Context7
Up-to-date docs for AI agents
제작자가 쓴 설명(영어 원문)
Durable, revision-pinned memory storage and retrieval for AI conversations.
이 세 가지는 절대 하나의 점수로 합치지 않아요. 의견, 측정, 인기는 서로 다른 것이니까요.
이 서버는 아직 쉬운 말로 된 요약을 쓰지 못했어요. 아래는 레지스트리에서 읽어 온 사실이에요.
쓰고 있는 AI 앱을 고른 다음 설정을 복사하세요.
필요한 것
어떤 앱을 쓰세요?
위에서 앱을 고르세요. 기억해 두었다가 다음부터는 버튼에 “…에 설치”라고 표시해요.
웹, 데스크톱, 모바일의 Claude에서 쓸 수 있어요:
https://mempersist.codifiedtech.id/mcp터미널에서 이 명령어를 실행하세요
claude mcp add --transport http mempersist https://mempersist.codifiedtech.id/mcp프로젝트의 .cursor/mcp.json 또는 ~/.cursor/mcp.json에 붙여 넣으세요
{
"mcpServers": {
"mempersist": {
"url": "https://mempersist.codifiedtech.id/mcp"
}
}
}브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.
프로젝트의 .vscode/mcp.json에 붙여 넣으세요
{
"servers": {
"mempersist": {
"type": "http",
"url": "https://mempersist.codifiedtech.id/mcp"
}
}
}브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.
ChatGPT는 인터넷에 있는 서버에만 연결할 수 있어요:
https://mempersist.codifiedtech.id/mcp메뉴 이름은 요금제나 시기에 따라 조금 다를 수 있어요.
선택한 앱은 이 기기의 쿠키에만 저장돼요. 계정은 필요 없어요.
이 설정은 제작자의 레지스트리 정보로 만들었어요. README와 다르면 README를 따르세요.
아직 이 서버의 도구 목록을 읽지 않았어요. 엔드포인트는 차례대로 돌아가며 점검해요.
누구나 볼 수 있는 정보를 점검했고, 코드는 읽지 않았어요. 해당하지 않는 항목은 개수에서 뺐어요. · 2026년 11월 7일 점검
레지스트리 이름이 GitHub 계정 ravhirizaldi 기준으로 확인되었고, 이 계정이 저장소를 소유하고 있어요
아직 GitHub에서 이 저장소를 읽어 오지 않았어요
아직 GitHub에서 이 저장소를 읽어 오지 않았어요
아직 점검하지 않았어요. 엔드포인트는 차례대로 돌아가며 점검해요
아직 점검하지 않았어요. 엔드포인트는 차례대로 돌아가며 점검해요
아직 점검하지 않았어요. 엔드포인트를 점검할 때 도구 목록을 읽어요
레지스트리에서 이 카테고리의 활성 서버 전체와 비교했어요. 스타는 게시자가 저장소를 소유한 경우에만 세요.
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.
레지스트리에 필수 키가 나와 있지 않아요. 다만 처음 쓸 때 로그인을 요구하는 서버도 있어요.
제작자의 클라우드에서 실행돼요. 설치 없이 인터넷으로 연결하지만, 보내는 내용은 제작자의 서버를 거쳐요.
GitHub 저장소는 마지막으로 – 변경됐고, 최신 버전(1.0.1)은 39일 전 레지스트리에 올라왔어요.
Claude Desktop, Claude Code, Cursor, VS Code처럼 MCP를 지원하는 앱에서 쓸 수 있어요. URL로 연결되기 때문에, 원격 MCP 서버를 지원하는 앱(예: 개발자 모드의 ChatGPT)에서도 쓸 수 있어요.
같은 카테고리에는: Context7, Codebase Memory, Exa
같은 카테고리에서 다른 제작자가 만든 서버예요. 스타 순으로 정렬했어요.
카드 보는 법:★ GitHub 스타i세 기둥: 리뷰 · 점검 · 사용 정도i업데이트 = 최신 버전을 레지스트리에 공개한 날i
Up-to-date docs for AI agents
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
제작자의 저장소에서 쓰인 그대로 가져왔어요. PopNx MCP가 검토하거나 보증한 내용이 아니에요. HTML, 이미지, 스크립트는 제거했어요. 링크를 누르면 이 사이트를 벗어나요.
Long-term memory for AI conversations, running entirely on Cloudflare. Original ChatGPT exports and normalized conversation graphs live in R2, a D1 catalog makes them queryable, lexical and semantic indexes stay disposable, and MCP exposes compact retrieval plus intentional writes.
| MCP endpoint | https://mempersist.codifiedtech.id/mcp |
| Registry | io.github.ravhirizaldi/mempersist — version 1.0.1 |
| Runtime | Workers, D1, R2, Queues, Workers AI (BGE-M3), Vectorize, OAuth KV |
| Protocol | MCP v2 over stateless Streamable HTTP, OAuth 2.1 with PKCE S256 |
| Scope | Single-operator V1, one Worker, one TypeScript package |
What it does. Preserves every uploaded ChatGPT export byte-for-byte, normalizes branches and node metadata into revision-pinned canonical JSONL, indexes derived FTS and vector data, and answers search, context, and batch reads with deterministic IDs. Writes are intentional, revision-checked, and durable before indexing is queued.
What it refuses to do. It does not intercept ChatGPT traffic, extract replacement "facts", summarize with a model, or treat any index as canonical. No billing, organizations, or speculative multi-tenancy; no Durable Objects, Workflows, cron triggers, or containers. Deleting every chunk, FTS row, and vector does not delete memory. "Unlimited" means no application-level message quota — Cloudflare limits and billing still apply.
flowchart TD
IMP["ChatGPT data export (conversations.json)"] --> V WRITE["MCP writes from any client"] --> V V["Validation and stable IDs"] --> R2[("R2 canonical archive raw import + immutable revisions")] R2 --> D1[("D1 catalog imports, revisions, graph, R2 pointers")] D1 --> Q["Cloudflare Queues import and index jobs"] Q --> FTS[("D1 FTS5 lexical chunks")] Q --> AI["Workers AI BGE-M3"] --> VEC[("Vectorize embeddings")] FTS --> SEARCH["Normalized hybrid search plus recent-canonical fallback"] VEC --> SEARCH SEARCH --> OUT["HTTP API and OAuth-protected MCP"] R2 --> EXPORT["Lossless export and recovery"]
Two ingestion paths, and they stay independent: the ChatGPT data export parser accepts the native conversations.json format only, while writes arrive through MCP from whichever client the caller uses. Both converge on the same canonical revision model, so a memory created by a tool call and one imported from an export are read, pinned, and restored identically.
R2 is the source of truth. A canonical write completes before its index job is queued, and an indexing failure never reports that durable memory was lost. Rebuilds read R2, so an export never needs to be uploaded twice. Full detail in ARCHITECTURE.md and docs/storage-and-indexing.md.
yarn install
cp .dev.vars.example .dev.vars # set a long random MEMORY_API_TOKEN yarn types:bindings yarn db:migrate:local yarn dev
Requires WSL2/Linux, Node.js 22+, Yarn 1.22, and Wrangler 4.x authenticated with yarn wrangler whoami. Use Yarn only. Local D1, R2, KV, and Queues are simulated; Workers AI and Vectorize point at real remote bindings in the main configuration, while unit and integration tests never call remote AI.
MemPersist is a standard remote MCP server: stateless Streamable HTTP at https://mempersist.codifiedtech.id/mcp, OAuth 2.1 authorization code with PKCE S256, scope memory. Nothing in the endpoint is client-specific — the same handshake, tool contracts, and server instructions serve every caller. Point a client at the URL and it works:
| Client | How to add it |
|---|---|
| Claude Code | claude mcp add --transport http mempersist https://mempersist.codifiedtech.id/mcp, then finish the email prompt |
| Codex CLI, ChatGPT desktop, IDE extension | ~/.codex/config.toml (or project .codex/config.toml), then codex mcp login mempersist |
| Cursor, Claude Desktop, VS Code, Zed | add the URL as a remote (HTTP) MCP server in the client's MCP settings; the client starts the OAuth flow |
| ChatGPT | Developer mode, then add the URL as a custom MCP app |
| MCP Inspector, custom SDK clients | npx @modelcontextprotocol/inspector, or the official SDK client; use the URL and either OAuth or the developer token |
| stdio-only clients | keep the server remote and bridge stdio to HTTP with an OAuth-capable proxy; MemPersist itself never needs npx |
Codex configuration:
[mcp_servers.mempersist]
type = "remote" url = "https://mempersist.codifiedtech.id/mcp"
codex mcp login mempersist to authorize
The client discovers OAuth from the 401 challenge, opens the consent page, and stores the issued access and refresh tokens. The consent page takes an email and sends a single-use, 15-minute magic link through the EMAIL binding; the connection completes only after that link is opened, and an existing email reconnects to its archive. The single scope is memory, and the sender address is configuration (AUTH_EMAIL_FROM, LEGACY_AUTH_EMAIL_FROM), not part of the API contract. Never paste MEMORY_API_TOKEN into a connector.
Already-configured connections keep working across upgrades without re-authorization; the legacy hostname stays supported, and moving one client to the primary hostname costs exactly one new authorization.
Scripts, the CLI, and non-interactive automation may send Authorization: Bearer instead of OAuth, which always maps to the owner archive. Every account may own multiple namespaces; the same namespace name in two accounts is separate data, and a supplied namespace is honored only when the caller owns it.
The MCP audience is deployment configuration, so point a development server at itself:
yarn dev --local --port 8787 --local-protocol https \
--var MCP_ORIGIN_OVERRIDE:https://127.0.0.1:8787
Discovery, consent, and token audiences then use https://127.0.0.1:8787, and both the .dev.vars developer token and the full OAuth flow work. Local send_email writes each magic link to .wrangler/tmp/email/ /email-text/. See docs/development.md.
24 tools, each carrying a human-readable title and read-only or destructive annotations. Retrieve first, then expand only what you selected.
| Tool | Title | Notes |
|---|---|---|
memory_search | Search memories | Hybrid search, 1–20 references; filters and opaque cursor pagination |
memory_get_context | Get memory context | Canonical messages around one result chunk, up to 10 each way |
memory_get_conversation | Get conversation | Page one conversation's active timeline or full graph |
memory_get_messages | Get messages | Exact source-node or optional keyed lookup, revision-pinned, ordered batch with opaque cursor and byte budget |
memory_get_conversations | Get conversations | Revision-pinned batch read of 1–20 conversations, cursor-paged |
memory_list_conversations | List conversations | Metadata and tags only, no bodies |
memory_list_revisions | List revisions | Immutable revision history, newest first |
memory_resolve_conversations | Resolve conversations | Exact-title lookup, no semantic search |
memory_list_namespaces | List namespaces | Owned namespaces with conversation counts |
memory_stats | Get memory statistics | Per-namespace counts and indexing health |
memory_import_status | Get import status | Import progress, duplicate, or failure |
memory_get_capabilities | Get capabilities | The deployed contract: versions, limits, per-tool bounds, and message_keys / atomic_multi_conversation_commit feature flags |
memory_get_messages accepts 1–100 ordered selectors. Each selector names a conversation_id, optionally pins a revision_id, and uses exactly one of source_node_id (up to 200 characters) or the forward-compatible message_key (1–128 lowercase ASCII letters, digits, ., _, /, or -, starting and ending with a letter or digit). Omitted revisions pin each conversation's current head before any canonical R2 body is loaded; canonical loads are deduplicated by unique pinned revision, while duplicate selectors retain duplicate ordered results. The read-only lookup does not use FTS or Vectorize. Missing, foreign, deleted, or unknown conversations, revisions, nodes, and keys share the same bounded NOT_FOUND result. Duplicate canonical message keys return a bounded canonical-storage error and are never resolved by choosing one. Whole messages are admitted within the 32 KiB default, 4 KiB minimum, and 48 KiB maximum serialized budgets; an oversized message is not truncated and returns only bounded identity/byte diagnostics. Continuations use an opaque, HMAC-signed, tenant-bound cursor that preserves selector order and revision pins.
The optional message_key selector reads keyed fields written by memory_upsert_messages (and any canonical data that carries them). memory_upsert_messages is the stable-key writer for logical records; its contract is documented in the Write section below.
| Tool | Title | Notes |
|---|---|---|
memory_build_context | Build memory context | Deterministic, revision-pinned pack from 1–20 required conversations, optional hybrid evidence, explicit token and byte budgets |
Each write returns a bounded durable receipt with separate indexing and verification status, and accepts verify: true to reload t
앞부분만 보여 드려요. 나머지는 저장소에서 읽어 보세요