Cortex
개요
제작자가 쓴 설명(영어 원문)
Local multi-client RAG server over the Model Context Protocol.
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 정도i아주 새로움↓ 56/주 · ★ –
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
- 카테고리: 검색 및 AI 기억
- 입력해야 할 값: CORTEX_KB_PATH
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:
CORTEX_KB_PATH
필요한 것
- PyPIPython의 uv 설치(uvx 명령어용)
어떤 앱을 쓰세요?
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": {
"cortex": {
"command": "uvx",
"args": [
"cortex-local-rag",
"serve"
],
"env": {
"CORTEX_KB_PATH": "your-value"
}
}
}
}터미널에서 이 명령어를 실행하세요
claude mcp add cortex --env CORTEX_KB_PATH=your-value -- uvx cortex-local-rag serve실행하기 전에 빈 값을 채워 주세요.
또는 설정을 직접 복사하기
프로젝트의 .cursor/mcp.json 또는 ~/.cursor/mcp.json에 붙여 넣으세요
{
"mcpServers": {
"cortex": {
"command": "uvx",
"args": [
"cortex-local-rag",
"serve"
],
"env": {
"CORTEX_KB_PATH": "your-value"
}
}
}
}브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.
또는 설정을 직접 복사하기
프로젝트의 .vscode/mcp.json에 붙여 넣으세요
{
"servers": {
"cortex": {
"type": "stdio",
"command": "uvx",
"args": [
"cortex-local-rag",
"serve"
],
"env": {
"CORTEX_KB_PATH": "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
- Absolute path to the local knowledge base Cortex indexes and serves.
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 9일 점검
- ✓ 통과
제작자와 저장소 일치
레지스트리 이름이 GitHub 계정 VBlackJack 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 5732개 중 0%보다 스타가 많아요
- 이 카테고리의 다른 서버 5732개 중 68%보다 최근에 레지스트리에 공개됐어요
- 기본 점검 결과가 이 카테고리의 다른 서버 5732개 중 100%와 같거나 더 좋아요
레지스트리에서 이 카테고리의 활성 서버 전체와 비교했어요. 스타는 게시자가 저장소를 소유한 경우에만 세요.
자주 묻는 질문
Cortex, 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: CORTEX_KB_PATH
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(2026.1021.3)은 18일 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)도 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:↓ 주간 다운로드i★ GitHub 스타i세 기둥: 리뷰 · 점검 · 사용 정도i업데이트 = 최신 버전을 레지스트리에 공개한 날i
Codebase Memory
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Exa
Connect AI agents to Exa for web search, content fetching, and multi-step research.
제작자의 README
README 열기
제작자의 저장소에서 쓰인 그대로 가져왔어요. PopNx MCP가 검토하거나 보증한 내용이 아니에요. HTML, 이미지, 스크립트는 제거했어요. 링크를 누르면 이 사이트를 벗어나요.
Cortex - RAG MCP for a knowledge base
English | Français
Cortex is an MCP (Model Context Protocol) server that exposes semantic search over a local knowledge base. It lets Claude, Codex and Gemini find the right passage in your documents without wasting their context window. Search is semantic (by meaning, not keyword), in French and in English. Cortex processes and indexes the knowledge base locally without sending its content; the MCP client may still pass requested chunks to its model under its own policy. The optional Confluence writer only downloads explicitly allowlisted spaces; the generated Markdown, vector index, and lexical index remain local.
Starting with 2026.0906.01, Companion offers a guided home screen, operation history and Confluence setup from one page or space link. Connection and measured scope confirmation stay in the flow; successful collection is followed by indexing. Use the combined installer to keep Cortex and Companion compatible.
Since 2026.0909.02, Confluence updates preserve the served generation when subtree enumeration fails and apply changed target/classification settings on retry. Search uses multilingual vector retrieval by default; CLI and MCP callers can explicitly select hybrid or reranked search. The first successful collection after upgrading regenerates older publication revisions, and the following sync removes obsolete index entries.
Guided document updates (2026.0909.00)
Companion brings local documents and Confluence together in My sources, with one Update my documents action. Search previews are resizable, large page trees render visible rows, and cancelling review preparation keeps the draft. Readiness now follows the saved document folder and configuration, including after restart. Run one document update after upgrading to establish this evidence for older indexes. See the release notes.
Measured scope without enumerating the space (2026.0907.00)
Adding a Confluence source measures its page, subtree and whole-space scopes with one indexed count each instead of reading the space page by page. On a 5916-page space that measurement took 3 min 19 s, past the timeout of every graphical caller, so Companion showed nothing at all. It now answers in about a second, and the emitted contract is unchanged.
Two whole-space numbers shift by one as a result: the resolved page is no longer folded into the space total, and a space with no visible page reports zero rather than one. A deployment whose search endpoint returns no total cannot measure a scope and reports that as a permanent failure instead of a retryable one. See the contracts.
Paired Companion 2026.0907.00 restores the contrast of the scope window, whose options were drawn in the system text colour, and stops reporting a timeout as a connection failure or advising a delay increase that silently reverts.
Source management in Companion (2026.0906.02)
The workflow includes search, remote page trees, impact review, evidence-based readiness, save-and-update, last-removal undo and recovery actions. See the contracts.
Paired version 2026.0906.02 provides visible My sources cards, a prefilled selection editor, confirmed page/space removal and browser links to originals. Removal only changes Cortex tracking; search reflects it after successful collection and indexing.
Removing the final source explicitly writes spaces = [] in a schema v2 or v3 configuration. This intentional empty allowlist permits an empty publication with tombstones for prior documents. An absent spaces key remains incomplete configuration and collection is refused. Connection and credential validation and publication safeguards still apply. Both updated components are required; this capability is absent from the installed 2026.0906.01 release.
Installation
Windows, no Python (recommended)
The simplest path: one installer for Cortex, Cortex Companion, the windowless Confluence converter, and the offline models. No separate Python or .NET runtime is required.
- Download
Cortex-Setup.exeandSHA256SUMSfrom the latest release. - Before running the unsigned installer, calculate its digest with
Get-FileHash .\Cortex-Setup.exe -Algorithm SHA256in PowerShell and verify that it exactly matches theCortex-Setup.exeline inSHA256SUMS. - Double-click only after that check. If SmartScreen still warns, select
More info, thenRun anyway. - Choose the folder that holds your documents, keep
Index everything in this folder, and finish. Cortex Companion opens when installation completes. Indexing only starts when you request synchronization in Companion. - In Companion, open
Settingsand verify the knowledge-base folder. The Cortex executable installed with Companion is detected automatically. - Drop your documents in that folder, open
Local database, then selectSynchronize local documents. - Restart your AI application: Cortex shows up there as an MCP server.
Companion then lets you synchronize, schedule, diagnose, and configure Cortex without a terminal. Details, silent mode and reinstall: Windows install.
Standalone archives (Windows x64, macOS Apple Silicon, Linux x64)
Every release also ships one ZIP archive per platform. It unpacks to a cortex/ folder holding the cortex or cortex.exe executable (MCP server + CLI, no Python), its runtime, and the licenses for every embedded dependency; keep the folder whole. See Standalone distribution.
From PyPI (Python, advanced)
py -m pip install --upgrade cortex-local-rag
cortex setup
This path installs the CLI and MCP server, but not Cortex Companion. The model is downloaded on first use if its cache is empty.
From source (development)
:: From the folder where you cloned Cortex
install.bat
install.bat and sync.bat are the development path for a source checkout, not a supported end-user installation: install.bat installs the unlocked dependencies from requirements.txt, and sync.bat indexes the folder section by section without the Confluence documents. To use Cortex, install Cortex-Setup.exe or a standalone archive instead. Details: Setup.
How it works
Documents folder (.md, .pdf) Optional Confluence writer (REST)
| | | current Markdown generation +------------------+-------------------+ | v cortex sync <- Split, hash, vectorize, update FTS5 | v %LOCALAPPDATA%\Cortex\ <- ChromaDB + lexical.db | v cortex serve <- MCP server (FastMCP) | v MCP clients <- Claude / Codex / Gemini / Antigravity / LM Studio / Cursor / Windsurf / VS Code
The embedding model is the multilingual ONNX paraphrase-multilingual-MiniLM-L12-v2. The Windows installer bundles it; a source installation or standalone binary downloads it when the local cache is empty.
Two indexing modes
- Whole folder (default): anything you place in the chosen folder, at the root or in any subfolder, becomes searchable. Nothing to configure.
- Sections (advanced): limits indexing to named subfolders you can search separately (defaults
knowledge,projects,notes).
These modes govern the user-selected document folder. Generated ingestion documents are indexed separately from the current published generation with source_kind=doc and section sources.
Details: Configuration.
The cortex command
The installed package exposes a single command:
| Subcommand | Purpose |
|---|---|
cortex setup | Config + index + client registration in one go (--kb-path, --yes, --no-index, --reset). |
cortex serve | Runs the MCP server (used by clients). |
cortex sync | Incremental index synchronization. |
cortex search | Searches the index from the console (debugging aid). |
cortex ingestion | Shows source health and whether catch-up is due. |
cortex confluence | Stores the PAT interactively or runs the allowlisted writer. |
cortex config | Reads or changes configuration through an atomic JSON contract, notably for Companion. |
cortex daemon | Runs, inspects or stops the shared per-user server used when [server] mode = "shared" (opt-in). |
cortex bundle | Describes or verifies an encrypted portable archive. |
cortex doctor | Installation diagnostics (read-only). |
cortex register / cortex unregister | Adds or removes Cortex from MCP clients. |
cortex init | Creates the single per-user configuration. |
cortex check | Verifies the installation. |
cortex --help describes every subcommand and cortex --help describes its options. A prompt-free installation scripts as:
cortex setup --yes --kb-path "D:\Documents\Knowledge"
Exposed MCP tools
| Tool | Description |
|---|---|
cortex_search | Multilingual vector search by default; optional retrieval_mode (vector, hybrid, rerank). Parameters: query, section, top_k (1-10), source/author filters, and occurred/updated date ranges. |
cortex_sync | Triggers an incremental sync of the selected folder and, on a full sync, the current published document generation. |
cortex_list_sections | Lists included sections and "out of policy" folders. |
cortex_freshness | Read-only vault and ingestion freshness summary. Parameters: section (optional), include_entries (false by default). |
Documentation
- Table of contents
- Windows install: unified Cortex + Companion + Confluence converter + models installer, corpus choice, silent mode, reinstall.
- Standalone distribution: per-platform archives and reproducible builds.
- Install from source: prerequisites, MCP clients.
- User guide: sync, search, tools, doctor, logs.
- FAQ: installation, local data, sync, and diagnostics.
- Release notes: user-visible changes by version and the published-history notice.
- Technical changelog: complete changes by version.
- Configuration:
config.toml, indexing modes, sections, data home, migration. - Ingestion scheduling: source health, catch-up, retries, and Task Scheduler.
- Metadata v2 migration: structured search metadata, backup, migration, and restore.
- Confluence writer: allowlisted REST ingestion, Windows Credential Manager, conversion, and atomic generations.
- Reproducible install:
requirements.lock,--require-hashes, regenerating the lock. - Public specification: MCP surface, index contracts, data, distribution, and limits.
- Architecture: end-to-end and technical choices.
- Security: local runtime, telemetry off, single-writer.
Prerequisites
| Path | Requirements |
|---|---|
| Windows installer | No separate Python or .NET runtime. At least ~500 MB of space (applications, model + index). |
| Standalone archive | No Python. ~500 MB of space (model + index). |
| From source | Python 3.11 to 3.13. ~500 MB of space. |
| Client | Claude Desktop/Code, Codex, Gemini, Antigravity, LM Studio, Cursor, Windsurf or VS Code (MCP support). |
License
Apache 2.0. See LICENSE.
R
앞부분만 보여 드려요. 나머지는 저장소에서 읽어 보세요