Context7
Up-to-date docs for AI agents
Beschreibung vom Entwickler (englisches Original)
Local multi-client RAG server over the Model Context Protocol.
Diese drei werden nie zu einer Punktzahl zusammengefasst: Meinungen, Messungen und Beliebtheit sind verschiedene Dinge.
Für diesen Server haben wir noch keine Zusammenfassung in einfacher Sprache geschrieben. Unten stehen die Fakten, die wir aus der Registry gelesen haben.
Wähle die KI-App, die du nutzt, und kopiere die Einstellungen.
CORTEX_KB_PATHDu brauchst
Welche App nutzt du?
Wähle oben deine App. Wir merken sie uns, damit der Button beim nächsten Mal „In … installieren“ anzeigt.
Öffne Claude Desktop → Settings → Developer → Edit Config und füge dies in claude_desktop_config.json ein
{
"mcpServers": {
"cortex": {
"command": "uvx",
"args": [
"cortex-local-rag",
"serve"
],
"env": {
"CORTEX_KB_PATH": "your-value"
}
}
}
}Führe das in deinem Terminal aus
claude mcp add cortex --env CORTEX_KB_PATH=your-value -- uvx cortex-local-rag serveTrag die leeren Werte ein, bevor du ihn startest.
In .cursor/mcp.json in deinem Projekt oder in ~/.cursor/mcp.json einfügen
{
"mcpServers": {
"cortex": {
"command": "uvx",
"args": [
"cortex-local-rag",
"serve"
],
"env": {
"CORTEX_KB_PATH": "your-value"
}
}
}
}Dein Browser fragt, ob er die App öffnen darf, dann zeigt die App die Einstellungen und bittet dich um Bestätigung. Schlüsselwerte bleiben leer, damit du sie selbst einträgst.
In .vscode/mcp.json in deinem Projekt einfügen
{
"servers": {
"cortex": {
"type": "stdio",
"command": "uvx",
"args": [
"cortex-local-rag",
"serve"
],
"env": {
"CORTEX_KB_PATH": "your-value"
}
}
}
}Dein Browser fragt, ob er die App öffnen darf, dann zeigt die App die Einstellungen und bittet dich um Bestätigung. Schlüsselwerte bleiben leer, damit du sie selbst einträgst.
Dieser Server läuft auf deinem Computer, und ChatGPT kann sich nur mit Servern im Internet verbinden. Wähle eine andere App.
Deine Auswahl bleibt in einem Cookie auf diesem Gerät; kein Konto nötig.
Diese Einstellungen werden aus dem Registry-Eintrag des Entwicklers erzeugt. Wenn in der README etwas anderes steht, folge der README.
Läuft auf deinem Computer; die Tool-Liste erscheint nach der Installation in deiner KI-App.
Wir prüfen Informationen, die jeder sehen kann; den Code haben wir nicht gelesen. Checks, die nicht zutreffen, werden nicht mitgezählt. · Geprüft am 6. Nov. 2026
Der Registry-Name wurde mit dem GitHub-Konto VBlackJack bestätigt, dem das Repo gehört
Dieses Repo haben wir noch nicht von GitHub gelesen
Dieses Repo haben wir noch nicht von GitHub gelesen
Dieser Server läuft auf deinem Computer; es gibt keinen Endpunkt im Internet
Läuft auf deinem Computer und nutzt stattdessen lokale Einstellungen
Läuft auf deinem Computer; Tool-Listen können wir nur von Endpunkten im Internet lesen
Verglichen mit allen aktiven Servern dieser Kategorie in der Registry. Sterne zählen nur, wenn dem Herausgeber das Repo gehört.
Er hat 1 von 1 zutreffenden Basischecks bestanden. Den Code haben wir nicht gelesen. Bevor du einen Schlüssel oder Token hinzufügst, sieh nach, welche Zugriffe der Server verlangt, und nutze einen Schlüssel, der nur die Berechtigungen hat, die du brauchst.
Das musst du eintragen: CORTEX_KB_PATH
Er läuft auf deinem Computer. Deine KI-App startet ihn bei Bedarf, und die Daten laufen nicht über die Server des Entwicklers (außer der Server ruft selbst einen Onlinedienst auf).
Das GitHub-Repo wurde zuletzt – geändert, und die neueste Version (2026.1021.3) kam vor 16 Tagen in die Registry.
Apps, die MCP unterstützen, etwa Claude Desktop, Claude Code, Cursor und VS Code. Außerdem brauchst du Python (uv) auf deinem Computer.
In derselben Kategorie: Context7, Codebase Memory, Exa
Server derselben Kategorie von anderen Entwicklern, sortiert nach Sternen.
So liest du eine Karte:★ GitHub-SterneiDrei Säulen: Bewertungen · Checks · NutzungiAktualisiert = neueste Version in der Registry veröffentlichti
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.
Unverändert aus dem Repo des Entwicklers übernommen. PopNx MCP hat den Inhalt weder geprüft noch empfiehlt es ihn. HTML, Bilder und Skripte wurden entfernt. Links führen von dieser Website weg.
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.
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.
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.
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.
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.
Cortex-Setup.exe and SHA256SUMS from the latest release.Get-FileHash .\Cortex-Setup.exe -Algorithm SHA256 in PowerShell and verify that it exactly matches the Cortex-Setup.exe line in SHA256SUMS.More info, then Run anyway.Index everything in this folder, and finish. Cortex Companion opens when installation completes. Indexing only starts when you request synchronization in Companion.Settings and verify the knowledge-base folder. The Cortex executable installed with Companion is detected automatically.Local database, then select Synchronize local documents.Companion then lets you synchronize, schedule, diagnose, and configure Cortex without a terminal. Details, silent mode and reinstall: Windows install.
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.
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 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.
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.
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.
cortex commandThe 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"
| 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). |
config.toml, indexing modes, sections, data home, migration.requirements.lock, --require-hashes, regenerating the lock.| 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). |
Apache 2.0. See LICENSE.
Nur der Anfang wird gezeigt; den Rest findest du im Repo