Darwin RAG MCP
A local-first RAG engine that ingests documents, indexes them with BM25 and dense embeddings, and exposes search through an MCP server. It allows AI agents to search PDFs, notes, and other files privately on the user's machine without sending data to the cloud.
Package and access
Local package with source-attributed installation metadata. Koskamo does not execute packages during review.
Checks and signals
Each line is separate evidence, not a trust score.
- Popularity 3 GitHub stars
What you can do with it
- Ingest PDFs, Markdown, HTML, and spreadsheets into a local knowledge base
- Search indexed documents using hybrid, semantic, or keyword retrieval
- Generate LLM-backed answers synthesized from retrieved sources
- Configure MCP client integration for agents like Claude or Cursor
Source and maintenance
- Last repository push
- Latest release
- v0.2.14
- Maintenance checked
Packages and installation
Source-provided package data. Koskamo has not executed or live-probed this package.
darwin-rag 0.2.18
{
"version": "0.2.18",
"transport": "stdio",
"identifier": "darwin-rag",
"registryType": "pypi",
"registryBaseUrl": "https://pypi.org",
"packageArguments": [
{
"type": "positional",
"value": "mcp"
}
],
"environmentVariables": [
{
"name": "OPENAI_API_KEY",
"description": "OpenAI API key for LLM answer generation"
},
{
"name": "ANTHROPIC_API_KEY",
"description": "Anthropic API key for LLM answer generation"
},
{
"name": "GEMINI_API_KEY",
"description": "Google Gemini API key"
},
{
"name": "DARWIN_BASE_DIR",
"description": "Override the base data directory"
}
]
}Tools
Reported by the attributed source; not independently observed by Koskamo.
Maintenance history
Public check and source-refresh events. Editorial and ownership records remain private.
- · repository · passed · metadata changed · updated
- · backfill · recorded · Pre-expansion baseline; unobserved rich metadata remains unknown
Connect from your client
Each snippet configures the same source-provided package; replace placeholders before use.
Cursor
{
"mcpServers": {
"darwin-rag-mcp": {
"command": "uvx",
"args": [
"darwin-rag==0.2.18",
"mcp"
],
"env": {
"OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>",
"ANTHROPIC_API_KEY": "<YOUR_ANTHROPIC_API_KEY>",
"GEMINI_API_KEY": "<YOUR_GEMINI_API_KEY>",
"DARWIN_BASE_DIR": "<YOUR_DARWIN_BASE_DIR>"
}
}
}
}Cline
{
"mcpServers": {
"darwin-rag-mcp": {
"command": "uvx",
"args": [
"darwin-rag==0.2.18",
"mcp"
],
"env": {
"OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>",
"ANTHROPIC_API_KEY": "<YOUR_ANTHROPIC_API_KEY>",
"GEMINI_API_KEY": "<YOUR_GEMINI_API_KEY>",
"DARWIN_BASE_DIR": "<YOUR_DARWIN_BASE_DIR>"
}
}
}
}VS Code
{
"servers": {
"darwin-rag-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"darwin-rag==0.2.18",
"mcp"
],
"env": {
"OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>",
"ANTHROPIC_API_KEY": "<YOUR_ANTHROPIC_API_KEY>",
"GEMINI_API_KEY": "<YOUR_GEMINI_API_KEY>",
"DARWIN_BASE_DIR": "<YOUR_DARWIN_BASE_DIR>"
}
}
}
}Claude Desktop
{
"mcpServers": {
"darwin-rag-mcp": {
"command": "uvx",
"args": [
"darwin-rag==0.2.18",
"mcp"
],
"env": {
"OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>",
"ANTHROPIC_API_KEY": "<YOUR_ANTHROPIC_API_KEY>",
"GEMINI_API_KEY": "<YOUR_GEMINI_API_KEY>",
"DARWIN_BASE_DIR": "<YOUR_DARWIN_BASE_DIR>"
}
}
}
}Let your agent find its tools
Find servers like Darwin RAG MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.