Darwin RAG is listed as active in the registry but did not answer our last check. 345 installs a week from pypi. Last commit 27 Aug 2026.
Local-first RAG engine with MCP server for AI agent integration.
We read the source, 20 h ago · rules 3dff92dd89df
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.
return Path("/.dockerenv").exists() or (
result = subprocess.run(
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
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.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 13 min ago.
claude mcp add darwin-rag --transport http https://your-host.com/mcp
{
"mcpServers": {
"darwin-rag": {
"url": "https://your-host.com/mcp"
}
}
}
[mcp_servers.darwin-rag]
url = "https://your-host.com/mcp"
{
"mcpServers": {
"darwin-rag": {
"url": "https://your-host.com/mcp"
}
}
}
{
"mcpServers": {
"darwin-rag": {
"url": "https://your-host.com/mcp"
}
}
}
This one needs environment variables set before it will start:
OPENAI_API_KEY (OpenAI API key for LLM answer generation), ANTHROPIC_API_KEY (Anthropic API key for LLM answer generation), GEMINI_API_KEY (Google Gemini API key), DARWIN_BASE_DIR (Override the base data directory).
The author declared them in the registry entry; get the values from the project itself.
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://your-host.com/mcp | streamable-http | answering | 61 ms | 13 min ago |
Local FAISS vector database for RAG with document ingestion, semantic search, and MCP prompts.
Two-layer memory MCP server for AI agents with 37 tools, RAG, graphs, wiki, auth
Shared memory + orchestration for your coding agents. Local-first MCP, vector RAG.
Easy-to-setup local RAG server with minimal configuration
Local-first RAG MCP server: hybrid search over a folder of your own documents
Local-first memory for coding agents — MCP server, single SQLite file, local embeddings
Investment discipline MCP server with RAG, behavior detection, journaling, and market data.
Persistent memory for AI coding agents. Local-first SQLite + vector search. 17 MCP tools.
Answers built from our own checks of this server.