MCP Context Server

Name: MCP Context Server
Author: alex-feel

제작자: alex-feel버전 2.2.2i★ –i내 컴퓨터에서 실행

레지스트리 이름io.github.alex-feel/mcp-context-server

설치

개요

제작자가 쓴 설명(영어 원문)

An MCP server that provides persistent multimodal context storage for LLM agents.

PopNx MCP의 세 기둥

이 세 가지는 절대 하나의 점수로 합치지 않아요. 의견, 측정, 인기는 서로 다른 것이니까요.

사용자 의견i아직 리뷰가 없어요리뷰는 다음 단계에서 계정 기능과 함께 열려요
우리의 기본 점검i1개 중 1개 통과공개된 정보로 점검했으며, 코드는 아직 스캔하지 않았어요
사용 정도i아직 측정 안 함★ –

할 수 있는 일

이 서버는 아직 쉬운 말로 된 요약을 쓰지 못했어요. 아래는 레지스트리에서 읽어 온 사실이에요.

연결 방식: 내 컴퓨터에서 실행
전송 방식: stdio, Streamable HTTP
카테고리: 검색 및 AI 기억
입력해야 할 값: POSTGRESQL_CONNECTION_STRING, POSTGRESQL_PASSWORD, ANTHROPIC_API_KEY, OPENAI_API_KEY, AZURE_OPENAI_API_KEY, HUGGINGFACEHUB_API_TOKEN, VOYAGE_API_KEY, LANGSMITH_API_KEY, MCP_AUTH_TOKEN

설치

쓰고 있는 AI 앱을 고른 다음 설정을 복사하세요.

설치하기 전에

기본 점검: 1개 중 1개 통과
내 컴퓨터에서 내 사용자 계정의 권한(파일, 네트워크, 앱)으로 실행돼요.
직접 입력할 값: LOG_LEVEL, STORAGE_BACKEND, MAX_IMAGE_SIZE_MB, MAX_TOTAL_SIZE_MB, DB_PATH, POOL_MAX_READERS, POOL_MAX_WRITERS, POOL_CONNECTION_TIMEOUT_S, POOL_IDLE_TIMEOUT_S, POOL_HEALTH_CHECK_INTERVAL_S, RETRY_MAX_RETRIES, RETRY_BASE_DELAY_S, RETRY_MAX_DELAY_S, RETRY_JITTER, RETRY_BACKOFF_FACTOR, SQLITE_FOREIGN_KEYS, SQLITE_JOURNAL_MODE, SQLITE_SYNCHRONOUS, SQLITE_TEMP_STORE, SQLITE_MMAP_SIZE, SQLITE_CACHE_SIZE, SQLITE_PAGE_SIZE, SQLITE_WAL_AUTOCHECKPOINT, SQLITE_BUSY_TIMEOUT_MS, SQLITE_WAL_CHECKPOINT, SHUTDOWN_TIMEOUT_S, SHUTDOWN_TIMEOUT_TEST_S, QUEUE_TIMEOUT_S, QUEUE_TIMEOUT_TEST_S, CIRCUIT_BREAKER_FAILURE_THRESHOLD, CIRCUIT_BREAKER_RECOVERY_TIMEOUT_S, CIRCUIT_BREAKER_HALF_OPEN_MAX_CALLS, POSTGRESQL_CONNECTION_STRING, POSTGRESQL_HOST, POSTGRESQL_PORT, POSTGRESQL_USER, POSTGRESQL_PASSWORD, POSTGRESQL_DATABASE, POSTGRESQL_POOL_MIN, POSTGRESQL_POOL_MAX, POSTGRESQL_POOL_TIMEOUT_S, POSTGRESQL_COMMAND_TIMEOUT_S, POSTGRESQL_MIGRATION_TIMEOUT_S, POSTGRESQL_MAX_INACTIVE_LIFETIME_S, POSTGRESQL_MAX_QUERIES, POSTGRESQL_TCP_KEEPALIVES_IDLE_S, POSTGRESQL_TCP_KEEPALIVES_INTERVAL_S, POSTGRESQL_TCP_KEEPALIVES_COUNT, POSTGRESQL_STATEMENT_CACHE_SIZE, POSTGRESQL_MAX_CACHED_STATEMENT_LIFETIME_S, POSTGRESQL_MAX_CACHEABLE_STATEMENT_SIZE, POSTGRESQL_SSL_MODE, POSTGRESQL_SCHEMA, ENABLE_SEMANTIC_SEARCH, ENABLE_EMBEDDING_GENERATION, OLLAMA_HOST, OLLAMA_AUTO_PULL, OLLAMA_PULL_TIMEOUT_S, EMBEDDING_OLLAMA_TRUNCATE, EMBEDDING_OLLAMA_NUM_CTX, EMBEDDING_MODEL, EMBEDDING_DIM, EMBEDDING_TIMEOUT_S, EMBEDDING_RETRY_MAX_ATTEMPTS, EMBEDDING_RETRY_BASE_DELAY_S, EMBEDDING_MAX_CONCURRENT, ENABLE_SUMMARY_GENERATION, SUMMARY_PROVIDER, SUMMARY_MODEL, SUMMARY_MAX_TOKENS, SUMMARY_TIMEOUT_S, SUMMARY_RETRY_MAX_ATTEMPTS, SUMMARY_RETRY_BASE_DELAY_S, SUMMARY_MAX_CONCURRENT, SUMMARY_PROMPT, SUMMARY_MIN_CONTENT_LENGTH, SUMMARY_OLLAMA_NUM_CTX, SUMMARY_OLLAMA_TRUNCATE, SUMMARY_OPENAI_REASONING_EFFORT, SUMMARY_ANTHROPIC_EFFORT, ANTHROPIC_API_KEY, ENABLE_FTS, FTS_LANGUAGE, FTS_RERANK_WINDOW_SIZE, FTS_RERANK_GAP_MERGE, ENABLE_HYBRID_SEARCH, HYBRID_RRF_K, HYBRID_RRF_OVERFETCH, HYBRID_FTS_OR_THRESHOLD, SEARCH_DEFAULT_SORT_BY, SEARCH_TRUNCATION_LENGTH, ENABLE_CHUNKING, CHUNK_SIZE, CHUNK_OVERLAP, CHUNK_AGGREGATION, CHUNK_DEDUP_OVERFETCH, ENABLE_RERANKING, RERANKING_PROVIDER, RERANKING_MODEL, RERANKING_MAX_LENGTH, RERANKING_OVERFETCH, RERANKING_CACHE_DIR, RERANKING_CHARS_PER_TOKEN, RERANKING_INTRA_OP_THREADS, RERANKING_CPU_MEM_ARENA, RERANKING_BATCH_SIZE, EMBEDDING_PROVIDER, OPENAI_API_KEY, OPENAI_API_BASE, OPENAI_ORGANIZATION, AZURE_OPENAI_API_KEY, AZURE_OPENAI_ENDPOINT, AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME, AZURE_OPENAI_API_VERSION, HUGGINGFACEHUB_API_TOKEN, VOYAGE_API_KEY, VOYAGE_TRUNCATION, VOYAGE_BATCH_SIZE, LANGSMITH_TRACING, LANGSMITH_API_KEY, LANGSMITH_PROJECT, LANGSMITH_ENDPOINT, METADATA_INDEXED_FIELDS, METADATA_INDEX_SYNC_MODE, MCP_TRANSPORT, FASTMCP_HOST, FASTMCP_PORT, FASTMCP_STATELESS_HTTP, DISABLED_TOOLS, MCP_AUTH_TOKEN, MCP_AUTH_CLIENT_ID, MCP_AUTH_PROVIDER, MCP_SERVER_INSTRUCTIONS

비밀로 표시된 값은 내 계정의 열쇠예요. 절대 다른 사람과 공유하거나 채팅에 붙여 넣지 마세요.

필요한 것

PyPIPython의 uv 설치(uvx 명령어용)

어떤 앱을 쓰세요?

ClaudeClaude CodeCursorVS CodeChatGPT

위에서 앱을 고르세요. 기억해 두었다가 다음부터는 버튼에 “…에 설치”라고 표시해요.

Claude Desktop → Settings → Developer → Edit Config를 열고 claude_desktop_config.json에 이 내용을 붙여 넣으세요

{
  "mcpServers": {
    "context": {
      "command": "uvx",
      "args": [
        "mcp-context-server"
      ],
      "env": {
        "LOG_LEVEL": "your-value",
        "STORAGE_BACKEND": "your-value",
        "MAX_IMAGE_SIZE_MB": "your-value",
        "MAX_TOTAL_SIZE_MB": "your-value",
        "DB_PATH": "your-value",
        "POOL_MAX_READERS": "your-value",
        "POOL_MAX_WRITERS": "your-value",
        "POOL_CONNECTION_TIMEOUT_S": "your-value",
        "POOL_IDLE_TIMEOUT_S": "your-value",
        "POOL_HEALTH_CHECK_INTERVAL_S": "your-value",
        "RETRY_MAX_RETRIES": "your-value",
        "RETRY_BASE_DELAY_S": "your-value",
        "RETRY_MAX_DELAY_S": "your-value",
        "RETRY_JITTER": "your-value",
        "RETRY_BACKOFF_FACTOR": "your-value",
        "SQLITE_FOREIGN_KEYS": "your-value",
        "SQLITE_JOURNAL_MODE": "your-value",
        "SQLITE_SYNCHRONOUS": "your-value",
        "SQLITE_TEMP_STORE": "your-value",
        "SQLITE_MMAP_SIZE": "your-value",
        "SQLITE_CACHE_SIZE": "your-value",
        "SQLITE_PAGE_SIZE": "your-value",
        "SQLITE_WAL_AUTOCHECKPOINT": "your-value",
        "SQLITE_BUSY_TIMEOUT_MS": "your-value",
        "SQLITE_WAL_CHECKPOINT": "your-value",
        "SHUTDOWN_TIMEOUT_S": "your-value",
        "SHUTDOWN_TIMEOUT_TEST_S": "your-value",
        "QUEUE_TIMEOUT_S": "your-value",
        "QUEUE_TIMEOUT_TEST_S": "your-value",
        "CIRCUIT_BREAKER_FAILURE_THRESHOLD": "your-value",
        "CIRCUIT_BREAKER_RECOVERY_TIMEOUT_S": "your-value",
        "CIRCUIT_BREAKER_HALF_OPEN_MAX_CALLS": "your-value",
        "POSTGRESQL_CONNECTION_STRING": "your-value",
        "POSTGRESQL_HOST": "your-value",
        "POSTGRESQL_PORT": "your-value",
        "POSTGRESQL_USER": "your-value",
        "POSTGRESQL_PASSWORD": "your-value",
        "POSTGRESQL_DATABASE": "your-value",
        "POSTGRESQL_POOL_MIN": "your-value",
        "POSTGRESQL_POOL_MAX": "your-value",
        "POSTGRESQL_POOL_TIMEOUT_S": "your-value",
        "POSTGRESQL_COMMAND_TIMEOUT_S": "your-value",
        "POSTGRESQL_MIGRATION_TIMEOUT_S": "your-value",
        "POSTGRESQL_MAX_INACTIVE_LIFETIME_S": "your-value",
        "POSTGRESQL_MAX_QUERIES": "your-value",
        "POSTGRESQL_TCP_KEEPALIVES_IDLE_S": "your-value",
        "POSTGRESQL_TCP_KEEPALIVES_INTERVAL_S": "your-value",
        "POSTGRESQL_TCP_KEEPALIVES_COUNT": "your-value",
        "POSTGRESQL_STATEMENT_CACHE_SIZE": "your-value",
        "POSTGRESQL_MAX_CACHED_STATEMENT_LIFETIME_S": "your-value",
        "POSTGRESQL_MAX_CACHEABLE_STATEMENT_SIZE": "your-value",
        "POSTGRESQL_SSL_MODE": "your-value",
        "POSTGRESQL_SCHEMA": "your-value",
        "ENABLE_SEMANTIC_SEARCH": "your-value",
        "ENABLE_EMBEDDING_GENERATION": "your-value",
        "OLLAMA_HOST": "your-value",
        "OLLAMA_AUTO_PULL": "your-value",
        "OLLAMA_PULL_TIMEOUT_S": "your-value",
        "EMBEDDING_OLLAMA_TRUNCATE": "your-value",
        "EMBEDDING_OLLAMA_NUM_CTX": "your-value",
        "EMBEDDING_MODEL": "your-value",
        "EMBEDDING_DIM": "your-value",
        "EMBEDDING_TIMEOUT_S": "your-value",
        "EMBEDDING_RETRY_MAX_ATTEMPTS": "your-value",
        "EMBEDDING_RETRY_BASE_DELAY_S": "your-value",
        "EMBEDDING_MAX_CONCURRENT": "your-value",
        "ENABLE_SUMMARY_GENERATION": "your-value",
        "SUMMARY_PROVIDER": "your-value",
        "SUMMARY_MODEL": "your-value",
        "SUMMARY_MAX_TOKENS": "your-value",
        "SUMMARY_TIMEOUT_S": "your-value",
        "SUMMARY_RETRY_MAX_ATTEMPTS": "your-value",
        "SUMMARY_RETRY_BASE_DELAY_S": "your-value",
        "SUMMARY_MAX_CONCURRENT": "your-value",
        "SUMMARY_PROMPT": "your-value",
        "SUMMARY_MIN_CONTENT_LENGTH": "your-value",
        "SUMMARY_OLLAMA_NUM_CTX": "your-value",
        "SUMMARY_OLLAMA_TRUNCATE": "your-value",
        "SUMMARY_OPENAI_REASONING_EFFORT": "your-value",
        "SUMMARY_ANTHROPIC_EFFORT": "your-value",
        "ANTHROPIC_API_KEY": "your-value",
        "ENABLE_FTS": "your-value",
        "FTS_LANGUAGE": "your-value",
        "FTS_RERANK_WINDOW_SIZE": "your-value",
        "FTS_RERANK_GAP_MERGE": "your-value",
        "ENABLE_HYBRID_SEARCH": "your-value",
        "HYBRID_RRF_K": "your-value",
        "HYBRID_RRF_OVERFETCH": "your-value",
        "HYBRID_FTS_OR_THRESHOLD": "your-value",
        "SEARCH_DEFAULT_SORT_BY": "your-value",
        "SEARCH_TRUNCATION_LENGTH": "your-value",
        "ENABLE_CHUNKING": "your-value",
        "CHUNK_SIZE": "your-value",
        "CHUNK_OVERLAP": "your-value",
        "CHUNK_AGGREGATION": "your-value",
        "CHUNK_DEDUP_OVERFETCH": "your-value",
        "ENABLE_RERANKING": "your-value",
        "RERANKING_PROVIDER": "your-value",
        "RERANKING_MODEL": "your-value",
        "RERANKING_MAX_LENGTH": "your-value",
        "RERANKING_OVERFETCH": "your-value",
        "RERANKING_CACHE_DIR": "your-value",
        "RERANKING_CHARS_PER_TOKEN": "your-value",
        "RERANKING_INTRA_OP_THREADS": "your-value",
        "RERANKING_CPU_MEM_ARENA": "your-value",
        "RERANKING_BATCH_SIZE": "your-value",
        "EMBEDDING_PROVIDER": "your-value",
        "OPENAI_API_KEY": "your-value",
        "OPENAI_API_BASE": "your-value",
        "OPENAI_ORGANIZATION": "your-value",
        "AZURE_OPENAI_API_KEY": "your-value",
        "AZURE_OPENAI_ENDPOINT": "your-value",
        "AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME": "your-value",
        "AZURE_OPENAI_API_VERSION": "your-value",
        "HUGGINGFACEHUB_API_TOKEN": "your-value",
        "VOYAGE_API_KEY": "your-value",
        "VOYAGE_TRUNCATION": "your-value",
        "VOYAGE_BATCH_SIZE": "your-value",
        "LANGSMITH_TRACING": "your-value",
        "LANGSMITH_API_KEY": "your-value",
        "LANGSMITH_PROJECT": "your-value",
        "LANGSMITH_ENDPOINT": "your-value",
        "METADATA_INDEXED_FIELDS": "your-value",
        "METADATA_INDEX_SYNC_MODE": "your-value",
        "MCP_TRANSPORT": "your-value",
        "FASTMCP_HOST": "your-value",
        "FASTMCP_PORT": "your-value",
        "FASTMCP_STATELESS_HTTP": "your-value",
        "DISABLED_TOOLS": "your-value",
        "MCP_AUTH_TOKEN": "your-value",
        "MCP_AUTH_CLIENT_ID": "your-value",
        "MCP_AUTH_PROVIDER": "your-value",
        "MCP_SERVER_INSTRUCTIONS": "your-value"
      }
    }
  }
}

터미널에서 이 명령어를 실행하세요

claude mcp add context --env LOG_LEVEL=your-value --env STORAGE_BACKEND=your-value --env MAX_IMAGE_SIZE_MB=your-value --env MAX_TOTAL_SIZE_MB=your-value --env DB_PATH=your-value --env POOL_MAX_READERS=your-value --env POOL_MAX_WRITERS=your-value --env POOL_CONNECTION_TIMEOUT_S=your-value --env POOL_IDLE_TIMEOUT_S=your-value --env POOL_HEALTH_CHECK_INTERVAL_S=your-value --env RETRY_MAX_RETRIES=your-value --env RETRY_BASE_DELAY_S=your-value --env RETRY_MAX_DELAY_S=your-value --env RETRY_JITTER=your-value --env RETRY_BACKOFF_FACTOR=your-value --env SQLITE_FOREIGN_KEYS=your-value --env SQLITE_JOURNAL_MODE=your-value --env SQLITE_SYNCHRONOUS=your-value --env SQLITE_TEMP_STORE=your-value --env SQLITE_MMAP_SIZE=your-value --env SQLITE_CACHE_SIZE=your-value --env SQLITE_PAGE_SIZE=your-value --env SQLITE_WAL_AUTOCHECKPOINT=your-value --env SQLITE_BUSY_TIMEOUT_MS=your-value --env SQLITE_WAL_CHECKPOINT=your-value --env SHUTDOWN_TIMEOUT_S=your-value --env SHUTDOWN_TIMEOUT_TEST_S=your-value --env QUEUE_TIMEOUT_S=your-value --env QUEUE_TIMEOUT_TEST_S=your-value --env CIRCUIT_BREAKER_FAILURE_THRESHOLD=your-value --env CIRCUIT_BREAKER_RECOVERY_TIMEOUT_S=your-value --env CIRCUIT_BREAKER_HALF_OPEN_MAX_CALLS=your-value --env POSTGRESQL_CONNECTION_STRING=your-value --env POSTGRESQL_HOST=your-value --env POSTGRESQL_PORT=your-value --env POSTGRESQL_USER=your-value --env POSTGRESQL_PASSWORD=your-value --env POSTGRESQL_DATABASE=your-value --env POSTGRESQL_POOL_MIN=your-value --env POSTGRESQL_POOL_MAX=your-value --env POSTGRESQL_POOL_TIMEOUT_S=your-value --env POSTGRESQL_COMMAND_TIMEOUT_S=your-value --env POSTGRESQL_MIGRATION_TIMEOUT_S=your-value --env POSTGRESQL_MAX_INACTIVE_LIFETIME_S=your-value --env POSTGRESQL_MAX_QUERIES=your-value --env POSTGRESQL_TCP_KEEPALIVES_IDLE_S=your-value --env POSTGRESQL_TCP_KEEPALIVES_INTERVAL_S=your-value --env POSTGRESQL_TCP_KEEPALIVES_COUNT=your-value --env POSTGRESQL_STATEMENT_CACHE_SIZE=your-value --env POSTGRESQL_MAX_CACHED_STATEMENT_LIFETIME_S=your-value --env POSTGRESQL_MAX_CACHEABLE_STATEMENT_SIZE=your-value --env POSTGRESQL_SSL_MODE=your-value --env POSTGRESQL_SCHEMA=your-value --env ENABLE_SEMANTIC_SEARCH=your-value --env ENABLE_EMBEDDING_GENERATION=your-value --env OLLAMA_HOST=your-value --env OLLAMA_AUTO_PULL=your-value --env OLLAMA_PULL_TIMEOUT_S=your-value --env EMBEDDING_OLLAMA_TRUNCATE=your-value --env EMBEDDING_OLLAMA_NUM_CTX=your-value --env EMBEDDING_MODEL=your-value --env EMBEDDING_DIM=your-value --env EMBEDDING_TIMEOUT_S=your-value --env EMBEDDING_RETRY_MAX_ATTEMPTS=your-value --env EMBEDDING_RETRY_BASE_DELAY_S=your-value --env EMBEDDING_MAX_CONCURRENT=your-value --env ENABLE_SUMMARY_GENERATION=your-value --env SUMMARY_PROVIDER=your-value --env SUMMARY_MODEL=your-value --env SUMMARY_MAX_TOKENS=your-value --env SUMMARY_TIMEOUT_S=your-value --env SUMMARY_RETRY_MAX_ATTEMPTS=your-value --env SUMMARY_RETRY_BASE_DELAY_S=your-value --env SUMMARY_MAX_CONCURRENT=your-value --env SUMMARY_PROMPT=your-value --env SUMMARY_MIN_CONTENT_LENGTH=your-value --env SUMMARY_OLLAMA_NUM_CTX=your-value --env SUMMARY_OLLAMA_TRUNCATE=your-value --env SUMMARY_OPENAI_REASONING_EFFORT=your-value --env SUMMARY_ANTHROPIC_EFFORT=your-value --env ANTHROPIC_API_KEY=your-value --env ENABLE_FTS=your-value --env FTS_LANGUAGE=your-value --env FTS_RERANK_WINDOW_SIZE=your-value --env FTS_RERANK_GAP_MERGE=your-value --env ENABLE_HYBRID_SEARCH=your-value --env HYBRID_RRF_K=your-value --env HYBRID_RRF_OVERFETCH=your-value --env HYBRID_FTS_OR_THRESHOLD=your-value --env SEARCH_DEFAULT_SORT_BY=your-value --env SEARCH_TRUNCATION_LENGTH=your-value --env ENABLE_CHUNKING=your-value --env CHUNK_SIZE=your-value --env CHUNK_OVERLAP=your-value --env CHUNK_AGGREGATION=your-value --env CHUNK_DEDUP_OVERFETCH=your-value --env ENABLE_RERANKING=your-value --env RERANKING_PROVIDER=your-value --env RERANKING_MODEL=your-value --env RERANKING_MAX_LENGTH=your-value --env RERANKING_OVERFETCH=your-value --env RERANKING_CACHE_DIR=your-value --env RERANKING_CHARS_PER_TOKEN=your-value --env RERANKING_INTRA_OP_THREADS=your-value --env RERANKING_CPU_MEM_ARENA=your-value --env RERANKING_BATCH_SIZE=your-value --env EMBEDDING_PROVIDER=your-value --env OPENAI_API_KEY=your-value --env OPENAI_API_BASE=your-value --env OPENAI_ORGANIZATION=your-value --env AZURE_OPENAI_API_KEY=your-value --env AZURE_OPENAI_ENDPOINT=your-value --env AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME=your-value --env AZURE_OPENAI_API_VERSION=your-value --env HUGGINGFACEHUB_API_TOKEN=your-value --env VOYAGE_API_KEY=your-value --env VOYAGE_TRUNCATION=your-value --env VOYAGE_BATCH_SIZE=your-value --env LANGSMITH_TRACING=your-value --env LANGSMITH_API_KEY=your-value --env LANGSMITH_PROJECT=your-value --env LANGSMITH_ENDPOINT=your-value --env METADATA_INDEXED_FIELDS=your-value --env METADATA_INDEX_SYNC_MODE=your-value --env MCP_TRANSPORT=your-value --env FASTMCP_HOST=your-value --env FASTMCP_PORT=your-value --env FASTMCP_STATELESS_HTTP=your-value --env DISABLED_TOOLS=your-value --env MCP_AUTH_TOKEN=your-value --env MCP_AUTH_CLIENT_ID=your-value --env MCP_AUTH_PROVIDER=your-value --env MCP_SERVER_INSTRUCTIONS=your-value -- uvx mcp-context-server

실행하기 전에 빈 값을 채워 주세요.

Cursor에서 열기

또는 설정을 직접 복사하기

프로젝트의 .cursor/mcp.json 또는 ~/.cursor/mcp.json에 붙여 넣으세요

{
  "mcpServers": {
    "context": {
      "command": "uvx",
      "args": [
        "mcp-context-server"
      ],
      "env": {
        "LOG_LEVEL": "your-value",
        "STORAGE_BACKEND": "your-value",
        "MAX_IMAGE_SIZE_MB": "your-value",
        "MAX_TOTAL_SIZE_MB": "your-value",
        "DB_PATH": "your-value",
        "POOL_MAX_READERS": "your-value",
        "POOL_MAX_WRITERS": "your-value",
        "POOL_CONNECTION_TIMEOUT_S": "your-value",
        "POOL_IDLE_TIMEOUT_S": "your-value",
        "POOL_HEALTH_CHECK_INTERVAL_S": "your-value",
        "RETRY_MAX_RETRIES": "your-value",
        "RETRY_BASE_DELAY_S": "your-value",
        "RETRY_MAX_DELAY_S": "your-value",
        "RETRY_JITTER": "your-value",
        "RETRY_BACKOFF_FACTOR": "your-value",
        "SQLITE_FOREIGN_KEYS": "your-value",
        "SQLITE_JOURNAL_MODE": "your-value",
        "SQLITE_SYNCHRONOUS": "your-value",
        "SQLITE_TEMP_STORE": "your-value",
        "SQLITE_MMAP_SIZE": "your-value",
        "SQLITE_CACHE_SIZE": "your-value",
        "SQLITE_PAGE_SIZE": "your-value",
        "SQLITE_WAL_AUTOCHECKPOINT": "your-value",
        "SQLITE_BUSY_TIMEOUT_MS": "your-value",
        "SQLITE_WAL_CHECKPOINT": "your-value",
        "SHUTDOWN_TIMEOUT_S": "your-value",
        "SHUTDOWN_TIMEOUT_TEST_S": "your-value",
        "QUEUE_TIMEOUT_S": "your-value",
        "QUEUE_TIMEOUT_TEST_S": "your-value",
        "CIRCUIT_BREAKER_FAILURE_THRESHOLD": "your-value",
        "CIRCUIT_BREAKER_RECOVERY_TIMEOUT_S": "your-value",
        "CIRCUIT_BREAKER_HALF_OPEN_MAX_CALLS": "your-value",
        "POSTGRESQL_CONNECTION_STRING": "your-value",
        "POSTGRESQL_HOST": "your-value",
        "POSTGRESQL_PORT": "your-value",
        "POSTGRESQL_USER": "your-value",
        "POSTGRESQL_PASSWORD": "your-value",
        "POSTGRESQL_DATABASE": "your-value",
        "POSTGRESQL_POOL_MIN": "your-value",
        "POSTGRESQL_POOL_MAX": "your-value",
        "POSTGRESQL_POOL_TIMEOUT_S": "your-value",
        "POSTGRESQL_COMMAND_TIMEOUT_S": "your-value",
        "POSTGRESQL_MIGRATION_TIMEOUT_S": "your-value",
        "POSTGRESQL_MAX_INACTIVE_LIFETIME_S": "your-value",
        "POSTGRESQL_MAX_QUERIES": "your-value",
        "POSTGRESQL_TCP_KEEPALIVES_IDLE_S": "your-value",
        "POSTGRESQL_TCP_KEEPALIVES_INTERVAL_S": "your-value",
        "POSTGRESQL_TCP_KEEPALIVES_COUNT": "your-value",
        "POSTGRESQL_STATEMENT_CACHE_SIZE": "your-value",
        "POSTGRESQL_MAX_CACHED_STATEMENT_LIFETIME_S": "your-value",
        "POSTGRESQL_MAX_CACHEABLE_STATEMENT_SIZE": "your-value",
        "POSTGRESQL_SSL_MODE": "your-value",
        "POSTGRESQL_SCHEMA": "your-value",
        "ENABLE_SEMANTIC_SEARCH": "your-value",
        "ENABLE_EMBEDDING_GENERATION": "your-value",
        "OLLAMA_HOST": "your-value",
        "OLLAMA_AUTO_PULL": "your-value",
        "OLLAMA_PULL_TIMEOUT_S": "your-value",
        "EMBEDDING_OLLAMA_TRUNCATE": "your-value",
        "EMBEDDING_OLLAMA_NUM_CTX": "your-value",
        "EMBEDDING_MODEL": "your-value",
        "EMBEDDING_DIM": "your-value",
        "EMBEDDING_TIMEOUT_S": "your-value",
        "EMBEDDING_RETRY_MAX_ATTEMPTS": "your-value",
        "EMBEDDING_RETRY_BASE_DELAY_S": "your-value",
        "EMBEDDING_MAX_CONCURRENT": "your-value",
        "ENABLE_SUMMARY_GENERATION": "your-value",
        "SUMMARY_PROVIDER": "your-value",
        "SUMMARY_MODEL": "your-value",
        "SUMMARY_MAX_TOKENS": "your-value",
        "SUMMARY_TIMEOUT_S": "your-value",
        "SUMMARY_RETRY_MAX_ATTEMPTS": "your-value",
        "SUMMARY_RETRY_BASE_DELAY_S": "your-value",
        "SUMMARY_MAX_CONCURRENT": "your-value",
        "SUMMARY_PROMPT": "your-value",
        "SUMMARY_MIN_CONTENT_LENGTH": "your-value",
        "SUMMARY_OLLAMA_NUM_CTX": "your-value",
        "SUMMARY_OLLAMA_TRUNCATE": "your-value",
        "SUMMARY_OPENAI_REASONING_EFFORT": "your-value",
        "SUMMARY_ANTHROPIC_EFFORT": "your-value",
        "ANTHROPIC_API_KEY": "your-value",
        "ENABLE_FTS": "your-value",
        "FTS_LANGUAGE": "your-value",
        "FTS_RERANK_WINDOW_SIZE": "your-value",
        "FTS_RERANK_GAP_MERGE": "your-value",
        "ENABLE_HYBRID_SEARCH": "your-value",
        "HYBRID_RRF_K": "your-value",
        "HYBRID_RRF_OVERFETCH": "your-value",
        "HYBRID_FTS_OR_THRESHOLD": "your-value",
        "SEARCH_DEFAULT_SORT_BY": "your-value",
        "SEARCH_TRUNCATION_LENGTH": "your-value",
        "ENABLE_CHUNKING": "your-value",
        "CHUNK_SIZE": "your-value",
        "CHUNK_OVERLAP": "your-value",
        "CHUNK_AGGREGATION": "your-value",
        "CHUNK_DEDUP_OVERFETCH": "your-value",
        "ENABLE_RERANKING": "your-value",
        "RERANKING_PROVIDER": "your-value",
        "RERANKING_MODEL": "your-value",
        "RERANKING_MAX_LENGTH": "your-value",
        "RERANKING_OVERFETCH": "your-value",
        "RERANKING_CACHE_DIR": "your-value",
        "RERANKING_CHARS_PER_TOKEN": "your-value",
        "RERANKING_INTRA_OP_THREADS": "your-value",
        "RERANKING_CPU_MEM_ARENA": "your-value",
        "RERANKING_BATCH_SIZE": "your-value",
        "EMBEDDING_PROVIDER": "your-value",
        "OPENAI_API_KEY": "your-value",
        "OPENAI_API_BASE": "your-value",
        "OPENAI_ORGANIZATION": "your-value",
        "AZURE_OPENAI_API_KEY": "your-value",
        "AZURE_OPENAI_ENDPOINT": "your-value",
        "AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME": "your-value",
        "AZURE_OPENAI_API_VERSION": "your-value",
        "HUGGINGFACEHUB_API_TOKEN": "your-value",
        "VOYAGE_API_KEY": "your-value",
        "VOYAGE_TRUNCATION": "your-value",
        "VOYAGE_BATCH_SIZE": "your-value",
        "LANGSMITH_TRACING": "your-value",
        "LANGSMITH_API_KEY": "your-value",
        "LANGSMITH_PROJECT": "your-value",
        "LANGSMITH_ENDPOINT": "your-value",
        "METADATA_INDEXED_FIELDS": "your-value",
        "METADATA_INDEX_SYNC_MODE": "your-value",
        "MCP_TRANSPORT": "your-value",
        "FASTMCP_HOST": "your-value",
        "FASTMCP_PORT": "your-value",
        "FASTMCP_STATELESS_HTTP": "your-value",
        "DISABLED_TOOLS": "your-value",
        "MCP_AUTH_TOKEN": "your-value",
        "MCP_AUTH_CLIENT_ID": "your-value",
        "MCP_AUTH_PROVIDER": "your-value",
        "MCP_SERVER_INSTRUCTIONS": "your-value"
      }
    }
  }
}

브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.

VS Code에서 열기

또는 설정을 직접 복사하기

프로젝트의 .vscode/mcp.json에 붙여 넣으세요

{
  "servers": {
    "context": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "mcp-context-server"
      ],
      "env": {
        "LOG_LEVEL": "your-value",
        "STORAGE_BACKEND": "your-value",
        "MAX_IMAGE_SIZE_MB": "your-value",
        "MAX_TOTAL_SIZE_MB": "your-value",
        "DB_PATH": "your-value",
        "POOL_MAX_READERS": "your-value",
        "POOL_MAX_WRITERS": "your-value",
        "POOL_CONNECTION_TIMEOUT_S": "your-value",
        "POOL_IDLE_TIMEOUT_S": "your-value",
        "POOL_HEALTH_CHECK_INTERVAL_S": "your-value",
        "RETRY_MAX_RETRIES": "your-value",
        "RETRY_BASE_DELAY_S": "your-value",
        "RETRY_MAX_DELAY_S": "your-value",
        "RETRY_JITTER": "your-value",
        "RETRY_BACKOFF_FACTOR": "your-value",
        "SQLITE_FOREIGN_KEYS": "your-value",
        "SQLITE_JOURNAL_MODE": "your-value",
        "SQLITE_SYNCHRONOUS": "your-value",
        "SQLITE_TEMP_STORE": "your-value",
        "SQLITE_MMAP_SIZE": "your-value",
        "SQLITE_CACHE_SIZE": "your-value",
        "SQLITE_PAGE_SIZE": "your-value",
        "SQLITE_WAL_AUTOCHECKPOINT": "your-value",
        "SQLITE_BUSY_TIMEOUT_MS": "your-value",
        "SQLITE_WAL_CHECKPOINT": "your-value",
        "SHUTDOWN_TIMEOUT_S": "your-value",
        "SHUTDOWN_TIMEOUT_TEST_S": "your-value",
        "QUEUE_TIMEOUT_S": "your-value",
        "QUEUE_TIMEOUT_TEST_S": "your-value",
        "CIRCUIT_BREAKER_FAILURE_THRESHOLD": "your-value",
        "CIRCUIT_BREAKER_RECOVERY_TIMEOUT_S": "your-value",
        "CIRCUIT_BREAKER_HALF_OPEN_MAX_CALLS": "your-value",
        "POSTGRESQL_CONNECTION_STRING": "your-value",
        "POSTGRESQL_HOST": "your-value",
        "POSTGRESQL_PORT": "your-value",
        "POSTGRESQL_USER": "your-value",
        "POSTGRESQL_PASSWORD": "your-value",
        "POSTGRESQL_DATABASE": "your-value",
        "POSTGRESQL_POOL_MIN": "your-value",
        "POSTGRESQL_POOL_MAX": "your-value",
        "POSTGRESQL_POOL_TIMEOUT_S": "your-value",
        "POSTGRESQL_COMMAND_TIMEOUT_S": "your-value",
        "POSTGRESQL_MIGRATION_TIMEOUT_S": "your-value",
        "POSTGRESQL_MAX_INACTIVE_LIFETIME_S": "your-value",
        "POSTGRESQL_MAX_QUERIES": "your-value",
        "POSTGRESQL_TCP_KEEPALIVES_IDLE_S": "your-value",
        "POSTGRESQL_TCP_KEEPALIVES_INTERVAL_S": "your-value",
        "POSTGRESQL_TCP_KEEPALIVES_COUNT": "your-value",
        "POSTGRESQL_STATEMENT_CACHE_SIZE": "your-value",
        "POSTGRESQL_MAX_CACHED_STATEMENT_LIFETIME_S": "your-value",
        "POSTGRESQL_MAX_CACHEABLE_STATEMENT_SIZE": "your-value",
        "POSTGRESQL_SSL_MODE": "your-value",
        "POSTGRESQL_SCHEMA": "your-value",
        "ENABLE_SEMANTIC_SEARCH": "your-value",
        "ENABLE_EMBEDDING_GENERATION": "your-value",
        "OLLAMA_HOST": "your-value",
        "OLLAMA_AUTO_PULL": "your-value",
        "OLLAMA_PULL_TIMEOUT_S": "your-value",
        "EMBEDDING_OLLAMA_TRUNCATE": "your-value",
        "EMBEDDING_OLLAMA_NUM_CTX": "your-value",
        "EMBEDDING_MODEL": "your-value",
        "EMBEDDING_DIM": "your-value",
        "EMBEDDING_TIMEOUT_S": "your-value",
        "EMBEDDING_RETRY_MAX_ATTEMPTS": "your-value",
        "EMBEDDING_RETRY_BASE_DELAY_S": "your-value",
        "EMBEDDING_MAX_CONCURRENT": "your-value",
        "ENABLE_SUMMARY_GENERATION": "your-value",
        "SUMMARY_PROVIDER": "your-value",
        "SUMMARY_MODEL": "your-value",
        "SUMMARY_MAX_TOKENS": "your-value",
        "SUMMARY_TIMEOUT_S": "your-value",
        "SUMMARY_RETRY_MAX_ATTEMPTS": "your-value",
        "SUMMARY_RETRY_BASE_DELAY_S": "your-value",
        "SUMMARY_MAX_CONCURRENT": "your-value",
        "SUMMARY_PROMPT": "your-value",
        "SUMMARY_MIN_CONTENT_LENGTH": "your-value",
        "SUMMARY_OLLAMA_NUM_CTX": "your-value",
        "SUMMARY_OLLAMA_TRUNCATE": "your-value",
        "SUMMARY_OPENAI_REASONING_EFFORT": "your-value",
        "SUMMARY_ANTHROPIC_EFFORT": "your-value",
        "ANTHROPIC_API_KEY": "your-value",
        "ENABLE_FTS": "your-value",
        "FTS_LANGUAGE": "your-value",
        "FTS_RERANK_WINDOW_SIZE": "your-value",
        "FTS_RERANK_GAP_MERGE": "your-value",
        "ENABLE_HYBRID_SEARCH": "your-value",
        "HYBRID_RRF_K": "your-value",
        "HYBRID_RRF_OVERFETCH": "your-value",
        "HYBRID_FTS_OR_THRESHOLD": "your-value",
        "SEARCH_DEFAULT_SORT_BY": "your-value",
        "SEARCH_TRUNCATION_LENGTH": "your-value",
        "ENABLE_CHUNKING": "your-value",
        "CHUNK_SIZE": "your-value",
        "CHUNK_OVERLAP": "your-value",
        "CHUNK_AGGREGATION": "your-value",
        "CHUNK_DEDUP_OVERFETCH": "your-value",
        "ENABLE_RERANKING": "your-value",
        "RERANKING_PROVIDER": "your-value",
        "RERANKING_MODEL": "your-value",
        "RERANKING_MAX_LENGTH": "your-value",
        "RERANKING_OVERFETCH": "your-value",
        "RERANKING_CACHE_DIR": "your-value",
        "RERANKING_CHARS_PER_TOKEN": "your-value",
        "RERANKING_INTRA_OP_THREADS": "your-value",
        "RERANKING_CPU_MEM_ARENA": "your-value",
        "RERANKING_BATCH_SIZE": "your-value",
        "EMBEDDING_PROVIDER": "your-value",
        "OPENAI_API_KEY": "your-value",
        "OPENAI_API_BASE": "your-value",
        "OPENAI_ORGANIZATION": "your-value",
        "AZURE_OPENAI_API_KEY": "your-value",
        "AZURE_OPENAI_ENDPOINT": "your-value",
        "AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME": "your-value",
        "AZURE_OPENAI_API_VERSION": "your-value",
        "HUGGINGFACEHUB_API_TOKEN": "your-value",
        "VOYAGE_API_KEY": "your-value",
        "VOYAGE_TRUNCATION": "your-value",
        "VOYAGE_BATCH_SIZE": "your-value",
        "LANGSMITH_TRACING": "your-value",
        "LANGSMITH_API_KEY": "your-value",
        "LANGSMITH_PROJECT": "your-value",
        "LANGSMITH_ENDPOINT": "your-value",
        "METADATA_INDEXED_FIELDS": "your-value",
        "METADATA_INDEX_SYNC_MODE": "your-value",
        "MCP_TRANSPORT": "your-value",
        "FASTMCP_HOST": "your-value",
        "FASTMCP_PORT": "your-value",
        "FASTMCP_STATELESS_HTTP": "your-value",
        "DISABLED_TOOLS": "your-value",
        "MCP_AUTH_TOKEN": "your-value",
        "MCP_AUTH_CLIENT_ID": "your-value",
        "MCP_AUTH_PROVIDER": "your-value",
        "MCP_SERVER_INSTRUCTIONS": "your-value"
      }
    }
  }
}

브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.

이 서버는 내 컴퓨터에서 실행되는데, ChatGPT는 인터넷에 있는 서버에만 연결할 수 있어요. 다른 앱을 고르세요.

선택한 앱은 이 기기의 쿠키에만 저장돼요. 계정은 필요 없어요.

직접 입력할 값

LOG_LEVEL env
Log level
STORAGE_BACKEND env
Storage backend type: sqlite (default) or postgresql
MAX_IMAGE_SIZE_MB env
Maximum individual image size in megabytes
MAX_TOTAL_SIZE_MB env
Maximum total request size in megabytes
DB_PATH env
Custom database file location path
POOL_MAX_READERS env
Maximum number of concurrent read connections in the pool
POOL_MAX_WRITERS env
Maximum number of concurrent write connections in the pool
POOL_CONNECTION_TIMEOUT_S env
Connection timeout in seconds
POOL_IDLE_TIMEOUT_S env
Idle connection timeout in seconds
POOL_HEALTH_CHECK_INTERVAL_S env
Connection health check interval in seconds
RETRY_MAX_RETRIES env
Maximum number of retry attempts for failed operations
RETRY_BASE_DELAY_S env
Base delay in seconds between retry attempts
RETRY_MAX_DELAY_S env
Maximum delay in seconds between retry attempts
RETRY_JITTER env
Enable random jitter in retry delays
RETRY_BACKOFF_FACTOR env
Exponential backoff multiplication factor for retries
SQLITE_FOREIGN_KEYS env
Enable SQLite foreign key constraints
SQLITE_JOURNAL_MODE env
SQLite journal mode (e.g., WAL, DELETE)
SQLITE_SYNCHRONOUS env
SQLite synchronous mode (e.g., NORMAL, FULL, OFF)
SQLITE_TEMP_STORE env
SQLite temporary storage location (e.g., MEMORY, FILE)
SQLITE_MMAP_SIZE env
SQLite memory-mapped I/O size in bytes
SQLITE_CACHE_SIZE env
SQLite cache size (negative value for KB, positive for pages)
SQLITE_PAGE_SIZE env
SQLite page size in bytes
SQLITE_WAL_AUTOCHECKPOINT env
SQLite WAL autocheckpoint threshold in pages
SQLITE_BUSY_TIMEOUT_MS env
SQLite busy timeout in milliseconds
SQLITE_WAL_CHECKPOINT env
SQLite WAL checkpoint mode (e.g., PASSIVE, FULL, RESTART)
SHUTDOWN_TIMEOUT_S env
Server shutdown timeout in seconds
SHUTDOWN_TIMEOUT_TEST_S env
Test mode shutdown timeout in seconds
QUEUE_TIMEOUT_S env
Queue operation timeout in seconds
QUEUE_TIMEOUT_TEST_S env
Test mode queue timeout in seconds
CIRCUIT_BREAKER_FAILURE_THRESHOLD env
Circuit breaker failure threshold before opening
CIRCUIT_BREAKER_RECOVERY_TIMEOUT_S env
Circuit breaker recovery timeout in seconds
CIRCUIT_BREAKER_HALF_OPEN_MAX_CALLS env
Maximum calls allowed in circuit breaker half-open state
POSTGRESQL_CONNECTION_STRING 비밀 env
Complete PostgreSQL connection string (overrides individual settings if provided)
POSTGRESQL_HOST env
PostgreSQL server host address
POSTGRESQL_PORT env
PostgreSQL server port number
POSTGRESQL_USER env
PostgreSQL database username
POSTGRESQL_PASSWORD 비밀 env
PostgreSQL database password
POSTGRESQL_DATABASE env
PostgreSQL database name
POSTGRESQL_POOL_MIN env
PostgreSQL connection pool minimum size
POSTGRESQL_POOL_MAX env
PostgreSQL connection pool maximum size
POSTGRESQL_POOL_TIMEOUT_S env
PostgreSQL connection pool timeout in seconds
POSTGRESQL_COMMAND_TIMEOUT_S env
PostgreSQL command execution timeout in seconds
POSTGRESQL_MIGRATION_TIMEOUT_S env
Timeout in seconds for PostgreSQL migration operations (default: 300)
POSTGRESQL_MAX_INACTIVE_LIFETIME_S env
Close idle PostgreSQL connections after this many seconds (0 to disable, default: 300)
POSTGRESQL_MAX_QUERIES env
Recycle PostgreSQL connections after this many queries (0 to disable, default: 10000)
POSTGRESQL_TCP_KEEPALIVES_IDLE_S env
Seconds of idle time before sending first TCP keepalive probe (0 to disable, default: 15)
POSTGRESQL_TCP_KEEPALIVES_INTERVAL_S env
Seconds between subsequent TCP keepalive probes (0 to disable, default: 5)
POSTGRESQL_TCP_KEEPALIVES_COUNT env
Number of failed TCP keepalive probes before connection is considered dead (0 to disable, default: 3)
POSTGRESQL_STATEMENT_CACHE_SIZE env
asyncpg prepared statement cache size. Set to 0 for external pooler compatibility (PgBouncer transaction mode, Pgpool-II, etc.). Default: 100
POSTGRESQL_MAX_CACHED_STATEMENT_LIFETIME_S env
Maximum lifetime of cached prepared statements in seconds (default: 300). Has no effect when statement_cache_size=0
POSTGRESQL_MAX_CACHEABLE_STATEMENT_SIZE env
Maximum size of statement to cache in bytes (default: 15360). Has no effect when statement_cache_size=0
POSTGRESQL_SSL_MODE env
PostgreSQL SSL mode (disable, allow, prefer, require, verify-ca, verify-full)
POSTGRESQL_SCHEMA env
PostgreSQL schema name for table and index operations (default: public)
ENABLE_SEMANTIC_SEARCH env
Enable semantic search functionality
ENABLE_EMBEDDING_GENERATION env
Enable embedding generation for stored context. Default true - server fails if dependencies not met. Set false to disable embeddings.
OLLAMA_HOST env
Ollama API host URL for embedding generation
OLLAMA_AUTO_PULL env
Automatically pull missing Ollama models on startup (default: true)
OLLAMA_PULL_TIMEOUT_S env
Timeout in seconds for pulling Ollama models (default: 900, range: 30-3600)
EMBEDDING_OLLAMA_TRUNCATE env
Ollama embedding truncation mode: false (default) returns error when context exceeded, true enables silent truncation
EMBEDDING_OLLAMA_NUM_CTX env
Ollama embedding context window size in tokens (default: 4096, range: 512-2097152)
EMBEDDING_MODEL env
Embedding model name for semantic search
EMBEDDING_DIM env
Embedding vector dimensions
EMBEDDING_TIMEOUT_S env
Timeout in seconds for embedding generation API calls
EMBEDDING_RETRY_MAX_ATTEMPTS env
Maximum number of retry attempts for embedding generation
EMBEDDING_RETRY_BASE_DELAY_S env
Base delay in seconds between retry attempts (with exponential backoff)
EMBEDDING_MAX_CONCURRENT env
Maximum concurrent embedding generation operations (default: 3, range: 1-20)
ENABLE_SUMMARY_GENERATION env
Enable summary generation for stored context. Default true - server fails if dependencies not met. Set false to disable summaries.
SUMMARY_PROVIDER env
Summary provider: ollama (default), openai, or anthropic
SUMMARY_MODEL env
Summary generation model name (default: qwen3:0.6b)
SUMMARY_MAX_TOKENS env
Maximum output tokens for summary generation (default: 4000, range: 50-16384). Increase if summaries are truncated by reasoning models
SUMMARY_TIMEOUT_S env
Timeout in seconds for summary generation API calls
SUMMARY_RETRY_MAX_ATTEMPTS env
Maximum number of retry attempts for summary generation
SUMMARY_RETRY_BASE_DELAY_S env
Base delay in seconds between retry attempts (with exponential backoff)
SUMMARY_MAX_CONCURRENT env
Maximum concurrent summary generation operations (default: 3, range: 1-20)
SUMMARY_PROMPT env
Custom summarization prompt. Overrides the built-in default. Used as system message for the LLM.
SUMMARY_MIN_CONTENT_LENGTH env
Minimum text content length in characters to trigger summary generation (default: 500, range: 0-10000). Set to 0 to always generate.
SUMMARY_OLLAMA_NUM_CTX env
Ollama summary context window size in tokens (default: 32768, range: 512-2097152)
SUMMARY_OLLAMA_TRUNCATE env
Ollama summary truncation mode: false (default) returns error when context exceeded, true enables silent truncation
SUMMARY_OPENAI_REASONING_EFFORT env
Reasoning effort level for OpenAI reasoning models (default: low). Valid values vary by generation: gpt-5: low, medium, high; gpt-5.1+: none, low, medium, high, xhigh. Default low is universally vali…
SUMMARY_ANTHROPIC_EFFORT env
Effort level for Anthropic Claude models (default: none). Valid values: max, high, medium, low. Controls inference effort (adaptive thinking)
ANTHROPIC_API_KEY 비밀 env
Anthropic API key for summary generation
ENABLE_FTS env
Enable full-text search functionality
FTS_LANGUAGE env
Language for FTS stemming (e.g., english, german, french)
FTS_RERANK_WINDOW_SIZE env
Characters of context around each FTS match for reranking passage extraction (default: 750)
FTS_RERANK_GAP_MERGE env
Merge FTS match regions within this character distance (default: 100)
ENABLE_HYBRID_SEARCH env
Enable hybrid search combining FTS and semantic search with RRF fusion
HYBRID_RRF_K env
RRF smoothing constant for hybrid search (default 60)
HYBRID_RRF_OVERFETCH env
Multiplier for over-fetching results before RRF fusion (default: 2)
HYBRID_FTS_OR_THRESHOLD env
Minimum significant query terms to switch hybrid FTS from AND to OR logic (default: 4)
SEARCH_DEFAULT_SORT_BY env
Default sort order for search results: relevance (only 'relevance' supported in current version)
SEARCH_TRUNCATION_LENGTH env
Maximum character length for truncated text_content in search results (default: 300, range: 50-1000)
ENABLE_CHUNKING env
Enable text chunking for embedding generation (default: true)
CHUNK_SIZE env
Target chunk size in characters (default: 1500)
CHUNK_OVERLAP env
Overlap between chunks in characters (default: 150)
CHUNK_AGGREGATION env
Chunk score aggregation method: max (only 'max' supported in current version)
CHUNK_DEDUP_OVERFETCH env
Multiplier for over-fetching chunks before deduplication (default: 5)
ENABLE_RERANKING env
Enable cross-encoder reranking of search results (default: true)
RERANKING_PROVIDER env
Reranking provider (default: flashrank)
RERANKING_MODEL env
Reranking model name (default: ms-marco-MiniLM-L-12-v2)
RERANKING_MAX_LENGTH env
Maximum input length for reranking in tokens (default: 512)
RERANKING_OVERFETCH env
Multiplier for over-fetching results before reranking (default: 4)
RERANKING_CACHE_DIR env
Directory for caching reranking models
RERANKING_CHARS_PER_TOKEN env
Estimated characters per token for passage size validation (default: 4.0, range: 2.0-8.0)
RERANKING_INTRA_OP_THREADS env
ONNX Runtime intra-operation parallelism threads for reranking (default: 0 = auto-detect)
RERANKING_CPU_MEM_ARENA env
Enable ONNX Runtime CPU memory arena for reranking (default: false)
RERANKING_BATCH_SIZE env
Maximum passages per ONNX Runtime inference batch during reranking (default: 32)
EMBEDDING_PROVIDER env
Embedding provider: ollama (default), openai, azure, huggingface, or voyage
OPENAI_API_KEY 비밀 env
OpenAI API key for OpenAI embedding provider
OPENAI_API_BASE env
Custom base URL for OpenAI-compatible APIs
OPENAI_ORGANIZATION env
OpenAI organization ID
AZURE_OPENAI_API_KEY 비밀 env
Azure OpenAI API key
AZURE_OPENAI_ENDPOINT env
Azure OpenAI endpoint URL
AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME env
Azure OpenAI embedding deployment name
AZURE_OPENAI_API_VERSION env
Azure OpenAI API version (default: 2024-02-01)
HUGGINGFACEHUB_API_TOKEN 비밀 env
HuggingFace Hub API token for HuggingFace embedding provider
VOYAGE_API_KEY 비밀 env
Voyage AI API key for Voyage embedding provider
VOYAGE_TRUNCATION env
Voyage AI truncation mode: false (default) returns error when context exceeded, true enables silent truncation
VOYAGE_BATCH_SIZE env
Voyage AI batch size for embedding requests
LANGSMITH_TRACING env
Enable LangSmith tracing
LANGSMITH_API_KEY 비밀 env
LangSmith API key
LANGSMITH_PROJECT env
LangSmith project name
LANGSMITH_ENDPOINT env
LangSmith API endpoint URL
METADATA_INDEXED_FIELDS env
Comma-separated list of metadata fields to index (field:type format)
METADATA_INDEX_SYNC_MODE env
Index sync mode: strict (fail), auto (sync), warn (log), additive (default, add missing only)
MCP_TRANSPORT env
Transport mode: stdio for local, http for Docker/remote
FASTMCP_HOST env
HTTP bind address (use 0.0.0.0 for Docker)
FASTMCP_PORT env
HTTP port number
FASTMCP_STATELESS_HTTP env
Enable stateless HTTP mode for horizontal scaling. Enabled by default as the server has no stateful MCP features. Set to false only if you need server-side MCP session tracking.
DISABLED_TOOLS env
Comma-separated list of tools to disable (e.g., delete_context,update_context)
MCP_AUTH_TOKEN 비밀 env
Bearer token for HTTP authentication (required when using SimpleTokenVerifier)
MCP_AUTH_CLIENT_ID env
Client ID to assign to authenticated requests
MCP_AUTH_PROVIDER env
Authentication provider: none (default), simple_token
MCP_SERVER_INSTRUCTIONS env
Custom server instructions text. Overrides built-in default. Set to empty string to disable.

이 설정은 제작자의 레지스트리 정보로 만들었어요. README와 다르면 README를 따르세요.

할 수 있는 일

내 컴퓨터에서 실행돼요. 설치하면 AI 앱에 도구 목록이 나타나요.

기본 점검i

누구나 볼 수 있는 정보를 점검했고, 코드는 읽지 않았어요. 해당하지 않는 항목은 개수에서 뺐어요. · 2026년 11월 7일 점검

✓ 통과
제작자와 저장소 일치
레지스트리 이름이 GitHub 계정 alex-feel 기준으로 확인되었고, 이 계정이 저장소를 소유하고 있어요
… 아직 점검 안 함
계속 관리되고 있음
아직 GitHub에서 이 저장소를 읽어 오지 않았어요
… 아직 점검 안 함
라이선스 있음
아직 GitHub에서 이 저장소를 읽어 오지 않았어요
– 해당 없음
엔드포인트 응답
내 컴퓨터에서 실행되는 서버라 인터넷 엔드포인트가 없어요
– 해당 없음
OAuth로 로그인
내 컴퓨터에서 실행되며, 대신 로컬 설정을 사용해요
… 아직 점검 안 함
도구 설명에 숨겨진 지시 없음
내 컴퓨터에서 실행돼요. 도구 목록은 인터넷 엔드포인트가 있는 서버에서만 읽을 수 있어요

검색 및 AI 기억 카테고리의 다른 서버와 비교i

이 카테고리의 다른 서버 7249개 중 0%보다 스타가 많아요
이 카테고리의 다른 서버 7249개 중 7%보다 최근에 레지스트리에 공개됐어요
기본 점검 결과가 이 카테고리의 다른 서버 7249개 중 100%와 같거나 더 좋아요

레지스트리에서 이 카테고리의 활성 서버 전체와 비교했어요. 스타는 게시자가 저장소를 소유한 경우에만 세요.

자주 묻는 질문

MCP Context Server, 안전한가요?

해당하는 기본 점검 1개 중 1개를 통과했어요. 코드는 읽지 않았어요. 키나 토큰을 넣기 전에 서버가 어떤 권한을 요구하는지 확인하고, 꼭 필요한 권한만 있는 키를 쓰세요.

어떤 키나 코드가 필요한가요?

입력해야 할 값: POSTGRESQL_CONNECTION_STRING, POSTGRESQL_PASSWORD, ANTHROPIC_API_KEY, OPENAI_API_KEY, AZURE_OPENAI_API_KEY, HUGGINGFACEHUB_API_TOKEN, VOYAGE_API_KEY, LANGSMITH_API_KEY, MCP_AUTH_TOKEN

내 컴퓨터에서 실행되나요, 클라우드에서 실행되나요?

내 컴퓨터에서 실행돼요. AI 앱이 필요할 때 실행하고, 데이터는 제작자의 서버를 거치지 않아요(서버 자체가 온라인 서비스를 호출하는 경우는 제외).

아직 관리되고 있나요?

GitHub 저장소는 마지막으로 – 변경됐고, 최신 버전(2.2.2)은 7개월 전 레지스트리에 올라왔어요.

어떤 앱에서 쓸 수 있나요?

Claude Desktop, Claude Code, Cursor, VS Code처럼 MCP를 지원하는 앱에서 쓸 수 있어요. 내 컴퓨터에 Python (uv), Docker도 있어야 해요.

대신 쓸 수 있는 건 뭐가 있나요?

같은 카테고리에는: Context7, Codebase Memory, Exa

대안

같은 카테고리에서 다른 제작자가 만든 서버예요. 스타 순으로 정렬했어요.

카드 보는 법:★ GitHub 스타i세 기둥: 리뷰 · 점검 · 사용 정도i업데이트 = 최신 버전을 레지스트리에 공개한 날i

Context7

제작자: upstash

Up-to-date docs for AI agents

컴퓨터 또는 클라우드★ 64,224MIT오늘 업데이트

설치

Codebase Memory

제작자: DeusData

Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.

내 컴퓨터에서 실행★ 48,148MIT20일 전 업데이트

설치

Exa

제작자: exa-labs

Connect AI agents to Exa for web search, content fetching, and multi-step research.

클라우드에서 실행★ 5,213MIT지난달 업데이트

설치

제작자의 README

README 열기

제작자의 저장소에서 쓰인 그대로 가져왔어요. PopNx MCP가 검토하거나 보증한 내용이 아니에요. HTML, 이미지, 스크립트는 제거했어요. 링크를 누르면 이 사이트를 벗어나요.

MCP Context Server

A high-performance Model Context Protocol (MCP) server providing persistent multimodal context storage for LLM agents. Built with FastMCP, this server enables seamless context sharing across multiple agents working on the same task through thread-based scoping.

[!WARNING]

Upgrading from v2.x? Version 3.x.x uses a new database schema with UUIDv7 primary keys. Existing v2.x databases require a one-time data migration before they can be used with v3.x.x. The opt-in CLI mcp-context-server-migrate ships with the server.

See the [Migration Guide](docs/migration-v2-to-v3.md) before upgrading. Fresh installations are unaffected.

Key Features

Multimodal Context Storage: Store and retrieve both text and images
UUIDv7 Context Identifiers: Every context entry is identified by a 32-character lowercase hex UUIDv7 value, providing time-ordered, globally unique IDs with a stable lex-string ordering
Thread-Based Scoping: Agents working on the same task share context through thread IDs
Per-Record Access Control: Every entry has an owner, a private or public visibility, and optional user or group grants, enforced on every read, update and delete on both SQLite and PostgreSQL. With IdP-issued JWTs, each caller finds, counts and changes only the entries it may access, the owner of an entry shares it with users or groups through share_context, and every returned entry reports its visibility and whether the caller owns it. See the Access Model
Anonymous Read Access: Hand readers without an identity-provider account one shared token that reads public entries and can never write: the server refuses every write by the principal ACCESS_CONTROL_ANONYMOUS_PRINCIPAL names, and the token must expire. See Anonymous Read Access
PostgreSQL Row-Level Security (optional): With ENABLE_POSTGRESQL_RLS=true, PostgreSQL also enforces the access model in the database, so a defect in how a query applies the access rules cannot expose another principal's entries. Reads go through an owner-owned, role-gated view that keeps every search index in use. See Row-level security (PostgreSQL)
Flexible Metadata Filtering: Store custom structured data with any JSON-serializable fields and filter using 16 powerful operators
Date Range Filtering: Filter context entries by creation timestamp using ISO 8601 format
Tag-Based Organization: Efficient context retrieval with normalized, indexed tags
Summary Generation: Optional automatic LLM-based summarization returned alongside truncated text_content in all search tool results for better agent context efficiency (enabled by default with Ollama)
Full-Text Search: Linguistic search with stemming, ranking, boolean queries (FTS5/tsvector), and cross-encoder reranking. Auto-enabled by default (ENABLE_FTS=auto); needs no extra dependencies
Semantic Search: Vector similarity search for meaning-based retrieval with cross-encoder reranking. Auto-enabled by default (ENABLE_SEMANTIC_SEARCH=auto) whenever an embedding provider is available (embedding generation is on by default)
Hybrid Search: Combined FTS + semantic search using Reciprocal Rank Fusion (RRF) with cross-encoder reranking. Auto-enabled by default (ENABLE_HYBRID_SEARCH=auto) whenever at least one of full-text or semantic search is available
Server-Side Grep: Literal/regex, line-oriented, unranked pattern matching over stored records (grep_context) — the precise-locate complement to full-text/semantic search, with ripgrep-style output modes and bounded results. Auto-enabled by default (ENABLE_GREP_CONTEXT=auto), pure-Python so it behaves identically on SQLite and PostgreSQL
Record Navigation (index_tree): navigate_context builds an on-demand Markdown-heading table of contents per record, with the entry summary as the root node; optional per-node LLM summaries (on by default) enrich each section. Pair with read_context_range to extract any section
Partial Reads: read_context_range returns a slice of one record by character range, line range, or outline node_id — so an agent can read only the relevant span of a long record instead of the whole thing
Knowledge Base Sync: Host document corpora such as handbooks and runbooks in kb: threads that agents search and navigate like any other context. The mcp-context-ingest command uploads a directory of documents and keeps it in sync, storing new files, updating changed ones and removing deleted ones, planned by the read-only plan_context_sync tool (ENABLE_CONTEXT_SYNC=auto). See the Knowledge Base Guide
Cross-Encoder Reranking: Automatic result refinement using FlashRank cross-encoder models for improved search precision (enabled by default)
Embedding Compression (default ON): Reduces embedding storage by approximately 8x out of the box in v3.0.0. Bit-packed compressed vectors keep semantic and hybrid search working without changes to the tool surface, and the read path bypasses the pgvector >2000-dimension HNSW limit. Set ENABLE_EMBEDDING_COMPRESSION=false to opt out and keep fp32 storage. See the Embedding Compression Guide
Multiple Database Backends: Choose between SQLite (default, zero-config) or PostgreSQL (high-concurrency, production-grade)
High Performance: WAL mode (SQLite) / MVCC (PostgreSQL), strategic indexing, and async operations
MCP Standard Compliance: Works with Claude Code, LangGraph, and any MCP-compatible client
Production Ready: Comprehensive test coverage, type safety, and robust error handling

Connecting to Your AI Assistant

The fastest way to connect the MCP Context Server to Claude Code is the one-command Docker bootstrap.

For step-by-step instructions, prerequisites, troubleshooting, and update/uninstall commands, see the Connecting to Your AI Assistant Guide.

Environment Configuration

The server is fully configured via environment variables, supporting core settings, transport, authentication, embedding providers, summary generation, search features, database tuning, and more. Variables can be set in your MCP client configuration, in a .env file, or directly in the shell.

For the complete reference of all environment variables with types, defaults, constraints, and descriptions, see the Environment Variables Reference.

Summary Generation

Summary generation automatically creates concise LLM-based summaries for each stored context entry. Summaries are returned in the summary field of all search tool results alongside truncated text_content, providing dense, informative summaries that help agents determine relevance without fetching full entries.

For detailed instructions including all providers (Ollama, OpenAI, Anthropic), model selection, and custom prompt configuration, see the Summary Generation Guide.

Semantic Search

Semantic search is auto-enabled by default (ENABLE_SEMANTIC_SEARCH=auto): the semantic_search_context tool registers automatically whenever an embedding provider is available (embedding generation is on by default), and skips quietly otherwise. For detailed instructions on the multiple embedding providers (Ollama, OpenAI, Azure, HuggingFace, Voyage) and how to control the toggle explicitly, see the Semantic Search Guide.

Full-Text Search

Full-text search is auto-enabled by default (ENABLE_FTS=auto) and needs no extra dependencies, using the built-in database FTS engine (FTS5 on SQLite, tsvector on PostgreSQL). For linguistic processing, stemming, ranking, and boolean queries, see the Full-Text Search Guide.

Hybrid Search

Hybrid search is auto-enabled by default (ENABLE_HYBRID_SEARCH=auto): the hybrid_search_context tool registers automatically whenever at least one of full-text or semantic search is available. For combined FTS + semantic search using Reciprocal Rank Fusion (RRF), see the Hybrid Search Guide.

Metadata Filtering

For comprehensive metadata filtering including 16 operators, nested JSON paths, and performance optimization, see the Metadata Guide.

Database Backends

The server supports multiple database backends, selectable via the STORAGE_BACKEND environment variable. SQLite (default) provides zero-configuration local storage perfect for single-user deployments. PostgreSQL offers high-performance capabilities with 10x+ write throughput for multi-user and high-traffic deployments.

For detailed configuration instructions including PostgreSQL setup with Docker, Supabase integration, connection methods, and troubleshooting, see the Database Backends Guide.

API Reference

The MCP Context Server exposes 21 MCP tools for context management:

Core Operations: store_context, search_context, get_context_by_ids, delete_context, update_context, list_threads, get_statistics

Search Tools: semantic_search_context, fts_search_context, hybrid_search_context

Navigation Tools (locate / navigate / extract): grep_context, navigate_context, read_context_range

Sync Tools: plan_context_sync, list_ingest_state

Sharing Tools: share_context, unshare_context, list_context_grants

Batch Operations: store_context_batch, update_context_batch, delete_context_batch

For complete tool documentation including parameters, return values, filtering options, and examples, see the API Reference. For when to use grep vs full-text vs semantic search, the index_tree, and partial reads, see Grep, Navigation & Partial Reads. For hosting and syncing document corpora, see the Knowledge Base Guide.

Docker Deployment

For production deployments with HTTP transport and container orchestration, Docker Compose configurations are available for SQLite, PostgreSQL, and external PostgreSQL (Supabase). See the Docker Deployment Guide for setup instructions and client connection details.

Kubernetes Deployment

For Kubernetes deployments, a Helm chart is provided with configurable values for different environments. See the Helm Deployment Guide for installation instructions, or the Kubernetes Deployment Guide for general Kubernetes concepts.

Authentication

For HTTP transport deployments requiring authentication, see the Authentication Guide for bearer token and IdP-issued JWT configuration, sharing entries with users and groups, and anonymous read access through an operator-minted token.

Getting Help

Bug reports: Report a bug
**Fea

앞부분만 보여 드려요. 나머지는 저장소에서 읽어 보세요

MCP Context Server

개요

PopNx MCP의 세 기둥

할 수 있는 일

설치

설치하기 전에

직접 입력할 값

할 수 있는 일

기본 점검i

제작자와 저장소 일치

계속 관리되고 있음

라이선스 있음

엔드포인트 응답

OAuth로 로그인

도구 설명에 숨겨진 지시 없음

검색 및 AI 기억 카테고리의 다른 서버와 비교i

자주 묻는 질문

대안

Context7

Codebase Memory

Exa

제작자의 README

MCP Context Server

Key Features

Connecting to Your AI Assistant

Environment Configuration

Summary Generation

Semantic Search

Full-Text Search

Hybrid Search

Metadata Filtering

Database Backends

API Reference

Docker Deployment

Kubernetes Deployment

Authentication

Getting Help