Cortex - RAG MCP for a knowledge base

Francais | English

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.

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 Mes 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.

1. Download Cortex-Setup.exe and SHA256SUMS from the latest release.
2. Before running the unsigned installer, calculate its digest with Get-FileHash .\Cortex-Setup.exe -Algorithm SHA256 in PowerShell and verify that it exactly matches the Cortex-Setup.exe line in SHA256SUMS.
3. Double-click only after that check. If SmartScreen still warns, select More info, then Run anyway.
4. Choose the folder that holds your documents, keep Index everything in this folder, and finish. Cortex Companion opens when installation completes.
5. In Companion, open Réglages (Settings) and verify the knowledge-base folder. The Cortex executable installed with Companion is detected automatically.
6. Drop your documents in that folder, open Base locale (Local knowledge base), then select Synchroniser les documents locaux (Synchronize local documents).
7. 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 contains the single cortex or cortex.exe binary (MCP server + CLI, no Python) and the licenses for every embedded dependency. 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 (Python, advanced)

:: From the folder where you cloned Cortex
install.bat

install.bat initializes the configuration, installs the dependencies, offers to register Cortex in the detected MCP clients, and validates the installation. 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:

cortex --help describes every subcommand and cortex <command> --help describes its options. A prompt-free installation scripts as:

cortex setup --yes --kb-path "D:\Documents\Knowledge"

Exposed MCP tools

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

License

Apache 2.0. See LICENSE.

Retrieval validation

See the validation guide for the desktop JSON search contract, the isolated FR/EN relevance corpus, performance measurements and exact paired-commit checks.