Cortex runs on your own machine — the client starts it, so there is no endpoint to ping. 208 installs a week from pypi. Last commit 21 Oct 2026.
Local multi-client RAG server over the Model Context Protocol.
What the code does
We read the source, 1 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
completed = subprocess.run(
values = dict(os.environ if environ is None else environ)
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Connect this server
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add cortex -e 'CORTEX_KB_PATH=<CORTEX_KB_PATH>' -- uvx cortex-local-rag{
"mcpServers": {
"cortex": {
"command": "uvx",
"args": [
"cortex-local-rag"
],
"env": {
"CORTEX_KB_PATH": "<CORTEX_KB_PATH>"
}
}
}
}[mcp_servers.cortex]
command = "uvx"
args = ["cortex-local-rag"]
env = { CORTEX_KB_PATH = "<CORTEX_KB_PATH>" }{
"mcpServers": {
"cortex": {
"command": "uvx",
"args": [
"cortex-local-rag"
],
"env": {
"CORTEX_KB_PATH": "<CORTEX_KB_PATH>"
}
}
}
}{
"servers": {
"cortex": {
"type": "stdio",
"command": "uvx",
"args": [
"cortex-local-rag"
],
"env": {
"CORTEX_KB_PATH": "<CORTEX_KB_PATH>"
}
}
}
}Put your own value in place of
<CORTEX_KB_PATH> (Absolute path to the local knowledge base Cortex indexes and serves).
The author’s registry entry marks it as required.
Alternatives to Cortex
same job, measured the same wayModel Context Protocol server for the VectorMethods VideoVector media intelligence API.
RAG-enabled MCP server using Contextual AI. Supports single-agent and multi-agent modes.
Easy-to-setup local RAG server with minimal configuration
Lightweight local RAG MCP server. 40x token reduction.
MCP RAG server with hybrid search, multi-KB support, and AI-powered chunk contextualization.
Local-first RAG MCP server: hybrid search over a folder of your own documents
Local semantic search over Obsidian vaults via Smart Connections embeddings. Multi-vault, private.
Local RAG MCP server with hybrid search, PDF/DOCX support, and zero-config setup
Cortex — questions
Answers built from our own checks of this server.