Darwin RAG MCP server

Q: How do I add Darwin RAG MCP to Claude Code?

Run `claude mcp add --env ANTHROPIC_API_KEY= --env GEMINI_API_KEY= --env OPENAI_API_KEY= darwin -- uvx darwin-rag` in your terminal. Add `--scope user` to make it available in every project.

Q: How do I add Darwin RAG MCP to Cursor?

Open `~/.cursor/mcp.json` and add the server under `mcpServers`, using the Cursor config shown in the install section above.

✓ VerifiedCommit Oct 14, 2026

brightdotdev/darwin · python · MIT

Enables AI agents to search and ingest local documents like PDFs, notes, and spreadsheets using a private, local-first RAG engine.

Also known as Brightdotdev/DARWIN, darwin, darwin-rag

stdio 11 tools Docs & Knowledge

Install GitHub ↗

Stars: 3
Tools: 11
Downloads, 30 days: 310
Latest version: 0.2.18
Last commit: Oct 14, 2026
License: MIT

What is Darwin RAG MCP?

Darwin RAG enables AI agents to search and ingest local documents like PDFs, notes, and spreadsheets using a private, local-first RAG engine. It exposes 11 tools, such as search_darwin, search_lists, get_search_results.

Summary generated from the project's README

About Darwin RAG MCP server

Darwin RAG provides a local-first retrieval-augmented generation engine designed for developers who want to connect their private documents to AI agents. It allows clients like Claude Desktop and Cursor to search through PDFs, Markdown files, spreadsheets, and even web pages without uploading sensitive data to a cloud index. The system uses a hybrid approach, combining BM25 keyword matching with dense embeddings to ensure high-quality retrieval.

Users can run the server locally via stdio for direct agent integration or deploy it as a remote service using SSE or Streamable HTTP. While the initial setup requires internet access to download embedding models, all subsequent indexing and search operations function fully offline. To enable answer synthesis, you must provide an API key for an LLM provider such as OpenAI, Anthropic, or Gemini through environment variables. The server includes specialized tools for managing data stores, inspecting file schemas, and running ingestion pipelines.

What you can do with it

1Private document ingestionInstruct an AI agent to index a local folder containing various file types for future querying.
2Hybrid knowledge retrievalPerform searches that combine exact keyword matching with semantic meaning to find relevant information.
3Structured data queryingSearch through organized files like CSVs or JSON arrays using specific field values.
4Isolated project managementCreate separate data stores to keep different projects or tenants completely independent.

Written from the project's README. Every use case is checked against a quote from it.

How to install Darwin RAG MCP

Formats verified 10 Nov 2026

Claude CodeCursorVS CodeClaude DesktopCodexGemini CLI

$ claude mcp add --env ANTHROPIC_API_KEY=<YOUR_ANTHROPIC_API_KEY> --env GEMINI_API_KEY=<YOUR_GEMINI_API_KEY> --env OPENAI_API_KEY=<YOUR_OPENAI_API_KEY> darwin -- uvx darwin-rag

~/.cursor/mcp.json

{
  "mcpServers": {
    "darwin": {
      "command": "uvx",
      "args": [
        "darwin-rag"
      ],
      "env": {
        "ANTHROPIC_API_KEY": "<YOUR_ANTHROPIC_API_KEY>",
        "GEMINI_API_KEY": "<YOUR_GEMINI_API_KEY>",
        "OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>"
      }
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "darwin": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "darwin-rag"
      ],
      "env": {
        "ANTHROPIC_API_KEY": "<YOUR_ANTHROPIC_API_KEY>",
        "GEMINI_API_KEY": "<YOUR_GEMINI_API_KEY>",
        "OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>"
      }
    }
  }
}

claude_desktop_config.json

{
  "mcpServers": {
    "darwin": {
      "command": "uvx",
      "args": [
        "darwin-rag"
      ],
      "env": {
        "ANTHROPIC_API_KEY": "<YOUR_ANTHROPIC_API_KEY>",
        "GEMINI_API_KEY": "<YOUR_GEMINI_API_KEY>",
        "OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>"
      }
    }
  }
}

~/.codex/config.toml

[mcp_servers.darwin]
command = "uvx"
args = ["darwin-rag"]

[mcp_servers.darwin.env]
ANTHROPIC_API_KEY = "<YOUR_ANTHROPIC_API_KEY>"
GEMINI_API_KEY = "<YOUR_GEMINI_API_KEY>"
OPENAI_API_KEY = "<YOUR_OPENAI_API_KEY>"

~/.gemini/settings.json

{
  "mcpServers": {
    "darwin": {
      "command": "uvx",
      "args": [
        "darwin-rag"
      ],
      "env": {
        "ANTHROPIC_API_KEY": "<YOUR_ANTHROPIC_API_KEY>",
        "GEMINI_API_KEY": "<YOUR_GEMINI_API_KEY>",
        "OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>"
      }
    }
  }
}

Set 4 environment variables before starting the server (below).Setup guides:Claude Code Cursor VS Code Claude Desktop

Darwin RAG MCP tools 11

Detected from the README

search_darwin
search_lists
get_search_results
get_search_result_by_id
get_schema
run_pipeline
purge_artifacts
create_store
list_files
file_status
get_logs

search_darwin	—
search_lists	—
get_search_results	—
get_search_result_by_id	—
get_schema	—
run_pipeline	—
purge_artifacts	—
create_store	—
list_files	—
file_status	—
get_logs	—

Configuration

ANTHROPIC_API_KEYSecret
Anthropic API key for LLM answer generation
GEMINI_API_KEYSecret
Google Gemini API key
OPENAI_API_KEYSecret
OpenAI API key for LLM answer generation
DARWIN_BASE_DIR
Override the base data directory

Name	Description
ANTHROPIC_API_KEY	Anthropic API key for LLM answer generation	Secret
GEMINI_API_KEY	Google Gemini API key	Secret
OPENAI_API_KEY	OpenAI API key for LLM answer generation	Secret
DARWIN_BASE_DIR	Override the base data directory

Automated checks

Ran Nov 12, 2026Full report →

100/100

Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work

Show this score in your README

Source repository linked and reachablePass
Open source license (OSI)Pass
Commit or release in the last yearPass
Package name not close to a popular packagePass
Remote endpoint uses HTTPSNot checked
Destructive tools are labelledNot checked
No hidden instructions to the modelPass
No critical advisory in the package or its dependenciesPass

README

View on GitHub

Darwin RAG

Search your own documents with any AI agent, privately, on your own machine.

Darwin is a local-first RAG engine that ingests documents, indexes them with BM25 + dense embeddings, and exposes search through an MCP server. Point Claude, Cursor, or any MCP client at it and your agent can search your PDFs, notes, spreadsheets, and web pages without sending them to a cloud index.

One-time internet is needed to download models during setup. After that, search and indexing run fully offline.

Ingestion: PDF, Markdown, HTML, images (OCR), CSV, Excel, ODS, URLs
Indexing: BM25 keyword + dense embedding hybrid index with configurable chunking strategies
Search: Hybrid, semantic, or keyword retrieval with reranking, diversity rerank, and structural penalties
Generation: LLM-backed answer synthesis via LiteLLM (OpenAI, Anthropic, Gemini, etc.)
Observability: Structured logging with per-session history, queryable via MCP
Isolation: Multiple independent stores for tenant/project separation
Deployment: stdio (AI agent subprocess), SSE, or Streamable HTTP; Docker-ready
Local-first: Everything runs locally, fully offline-capable after setup

Built by BrightDotDev.

Why Darwin?

Private by default. Your documents stay on your machine.
Works with your agent. Standard MCP server: Claude Desktop, Cursor, and other MCP clients.
Search that fits the question. Keyword for exact terms, semantic for meaning, hybrid when unsure.
Light to start. The required preset downloads just one embedding model.

Quick Start

1. Install

pip install darwin-rag

2. Set up models

# Interactive: detects hardware, pick your models
darwin-admin setup interactive

# Or one-shot (embedding-only, no prompts)
darwin-admin setup --preset required

3. Start the MCP server & connect

# stdio mode: for AI agent subprocess (Claude Desktop, Cursor, etc.)
darwin mcp

# Or HTTP mode: for remote clients
darwin mcp --http --port 8765

Configure your MCP client:

{
  "mcpServers": {
    "darwin": {
      "command": "darwin",
      "args": ["mcp"],
      "env": {
        "OPENAI_API_KEY": "sk-..."  // At least one LLM provider key
      }
    }
  }
}

Or generate config automatically:

darwin config claude          # Claude Desktop config
darwin config cursor          # Cursor config
darwin config all --copy      # All clients + copy to clipboard

4. Try it

Ask your agent: "Ingest ./my-notes with Darwin, then find everything I wrote about ."

Use it as an agent skill

Darwin ships with a skill (skills/darwin-rag/SKILL.md) that tells agents when and how to use the MCP tools: check what's indexed, ingest, pick a search mode, and answer from sources. Copy the darwin-rag folder into your agent's skills directory (for Claude Code: ~/.claude/skills/).

MCP Tools

Tool	Description
`search_darwin`	Query the knowledge base with hybrid/semantic/keyword search
`search_lists`	Search structured data (CSVs, JSON arrays) by field values
`get_search_results`	List saved search results
`get_search_result_by_id`	Load a saved search result by filename
`get_schema`	Inspect schemas for structured files (keys, types, record counts)
`run_pipeline`	Ingest + index documents from a path or URL
`purge_artifacts`	Delete pipeline artifacts for specific files
`create_store`	Create a new isolated data store
`list_files`	List all tracked files with pipeline status
`file_status`	Detailed status for a single file across all stages
`get_logs`	Query session logs (oldest first, INFO excluded)

Full documentation: docs/mcp.md

Remote / HTTP Mode

Start the server on a network-accessible endpoint:

# SSE transport (legacy)
darwin mcp --sse --host 0.0.0.0 --port 8765

# Streamable HTTP transport (recommended for production)
darwin mcp --http --host 0.0.0.0 --port 8765

Configure your MCP client with the URL:

{
  "mcpServers": {
    "darwin": {
      "url": "http://your-host:8765/mcp"  // or /sse for SSE mode
    }
  }
}

Environment Variables

Variable	Required	Description
`OPENAI_API_KEY`	No*	OpenAI provider key
`ANTHROPIC_API_KEY`	No*	Anthropic provider key
`GEMINI_API_KEY`	No*	Google Gemini provider key
`MISTRAL_API_KEY`	No*	Mistral AI provider key
`GROQ_API_KEY`	No*	Groq provider key
`COHERE_API_KEY`	No*	Cohere provider key
`TOGETHER_API_KEY`	No*	Together AI provider key
`OPENROUTER_API_KEY`	No*	OpenRouter provider key
`DEEPSEEK_API_KEY`	No*	DeepSeek provider key
`DARWIN_BASE_DIR`	No	Override the base data directory
`NO_COLOR`	No	Set to any value to disable ANSI color output

* At least one LLM provider key is required for answer generation. Search/indexing works without any.

Setup Details

Command	What it does
`darwin-admin setup interactive`	Guided setup: detect hardware, choose models
`darwin-admin setup --preset required`	Download embedding model only (fastest)
`darwin-admin setup --preset recommended`	Embedding + reranker + OCR models
`darwin-admin setup logging`	Reconfigure logging only
`darwin-admin setup validate`	Validate current setup

See docs/setup.md for the full walkthrough including Docker, from-source install, and API key configuration.

CLI Reference

darwin: User CLI

Command	Description
`darwin mcp`	Start MCP server (stdio, `--sse` or `--http` for network)
`darwin config [client]`	Generate MCP client config

darwin-admin: Power-user CLI

Command	Description
`darwin-admin setup`	Setup models, logging, and configuration
`darwin-admin status`	System status overview
`darwin-admin models`	Model registry: list, install, switch, keys
`darwin-admin store`	Data store: status, files, audit, health, repair
`darwin-admin pipeline`	Ingestion pipeline: run, ingest, index, purge
`darwin-admin search`	Interactive search
`darwin-admin logs`	Structured log viewer and management
`darwin-admin system`	System information
`darwin-admin uninstall`	Remove Darwin data and configuration

See docs/admin.md for the full command reference.

Python API

For embedding darwin-rag as a library in your own app:

from core import Darwin

d = Darwin()
d.ingest("./papers", recursive=True)
results = d.search("what is this paper about")
records = d.search_records(filters={"status": "active"})

Full reference: docs/api.md

Documentation

Doc	What
setup.md	Full setup walkthrough
mcp.md	MCP server, tools, resources, transports
admin.md	Admin CLI reference
architecture.md	For developers and contributors
pipeline.md	Ingestion & indexing
retrieval.md	Search engine
storage.md	DarwinStore
models.md	Model registry & inference
logger.md	Structured logging
orchestrators.md	High-level business logic
api.md	Python API (Darwin class)

Contributing

Found a bug? Want to add something? You're welcome here.

Issues: open one at github.com/BrightDotDev/DARWIN/issues
Code: fork, branch, PR. Keep it minimal.
AI-generated code is fine, but you own what you ship. Test it before submitting.

Read CONTRIBUTING.md for the full guidelines.

License

MIT. See LICENSE.

Core architecture and implementation by BrightDotDev.

Read full README

Darwin RAG MCP questions

How do I add Darwin RAG MCP to Claude Code?

Run claude mcp add --env ANTHROPIC_API_KEY=<YOUR_ANTHROPIC_API_KEY> --env GEMINI_API_KEY=<YOUR_GEMINI_API_KEY> --env OPENAI_API_KEY=<YOUR_OPENAI_API_KEY> darwin -- uvx darwin-rag in your terminal. Add --scope user to make it available in every project.

How do I add Darwin RAG MCP to Cursor?

Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.

What tools does Darwin RAG MCP provide?

It exposes 11 tools, including search_darwin, search_lists, get_search_results, get_search_result_by_id, get_schema.

Does Darwin RAG work offline?

Yes, after an initial internet connection is used to download models during setup, all search and indexing operations run fully offline.

Is my data private?

Yes, Darwin is designed to be local-first, meaning your documents stay on your own machine rather than being sent to a cloud index.

Which AI clients can I use with Darwin?

It works with standard MCP clients such as Claude Desktop and Cursor.

Facts

Nov 13, 2026

Stars: 3
Downloads, 30 days: 310
Latest version: 0.2.18
Last commit: Oct 14, 2026
License: MIT
Transport: stdio
Package: darwin-rag

Brightdotdev ↗

Community publisher

Published by an independent maintainer.

Alternatives

Works with

Claude Code Cursor VS Code Claude Desktop Codex Gemini CLI Windsurf Devin

Badge for your README

Show your HostedMCP checks score. The badge links readers to install instructions for every client.

[![HostedMCP checks](https://api.hostedmcp.org/v1/badge/server/brightdotdev/darwin.svg)](https://hostedmcp.org/servers/brightdotdev/darwin/checks)

Maintainer?

Claim this listing to edit it and add the HostedMCP badge to your README.

Claim listing

Before you install

Servers run with the permissions you give them. Use the narrowest token or database role that does the job.

Darwin RAG MCP server

✓ VerifiedCommit Oct 14, 2026

brightdotdev/darwin · python · MIT

Enables AI agents to search and ingest local documents like PDFs, notes, and spreadsheets using a private, local-first RAG engine.

Also known as Brightdotdev/DARWIN, darwin, darwin-rag

stdio 11 tools Docs & Knowledge

Install GitHub ↗

Stars: 3
Tools: 11
Downloads, 30 days: 310
Latest version: 0.2.18
Last commit: Oct 14, 2026
License: MIT

What is Darwin RAG MCP?

Summary generated from the project's README

About Darwin RAG MCP server

What you can do with it

1Private document ingestionInstruct an AI agent to index a local folder containing various file types for future querying.
2Hybrid knowledge retrievalPerform searches that combine exact keyword matching with semantic meaning to find relevant information.
3Structured data queryingSearch through organized files like CSVs or JSON arrays using specific field values.
4Isolated project managementCreate separate data stores to keep different projects or tenants completely independent.

Written from the project's README. Every use case is checked against a quote from it.

How to install Darwin RAG MCP

Formats verified 10 Nov 2026

Claude CodeCursorVS CodeClaude DesktopCodexGemini CLI

$ claude mcp add --env ANTHROPIC_API_KEY=<YOUR_ANTHROPIC_API_KEY> --env GEMINI_API_KEY=<YOUR_GEMINI_API_KEY> --env OPENAI_API_KEY=<YOUR_OPENAI_API_KEY> darwin -- uvx darwin-rag

~/.cursor/mcp.json

{
  "mcpServers": {
    "darwin": {
      "command": "uvx",
      "args": [
        "darwin-rag"
      ],
      "env": {
        "ANTHROPIC_API_KEY": "<YOUR_ANTHROPIC_API_KEY>",
        "GEMINI_API_KEY": "<YOUR_GEMINI_API_KEY>",
        "OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>"
      }
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "darwin": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "darwin-rag"
      ],
      "env": {
        "ANTHROPIC_API_KEY": "<YOUR_ANTHROPIC_API_KEY>",
        "GEMINI_API_KEY": "<YOUR_GEMINI_API_KEY>",
        "OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>"
      }
    }
  }
}

claude_desktop_config.json

{
  "mcpServers": {
    "darwin": {
      "command": "uvx",
      "args": [
        "darwin-rag"
      ],
      "env": {
        "ANTHROPIC_API_KEY": "<YOUR_ANTHROPIC_API_KEY>",
        "GEMINI_API_KEY": "<YOUR_GEMINI_API_KEY>",
        "OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>"
      }
    }
  }
}

~/.codex/config.toml

[mcp_servers.darwin]
command = "uvx"
args = ["darwin-rag"]

[mcp_servers.darwin.env]
ANTHROPIC_API_KEY = "<YOUR_ANTHROPIC_API_KEY>"
GEMINI_API_KEY = "<YOUR_GEMINI_API_KEY>"
OPENAI_API_KEY = "<YOUR_OPENAI_API_KEY>"

~/.gemini/settings.json

{
  "mcpServers": {
    "darwin": {
      "command": "uvx",
      "args": [
        "darwin-rag"
      ],
      "env": {
        "ANTHROPIC_API_KEY": "<YOUR_ANTHROPIC_API_KEY>",
        "GEMINI_API_KEY": "<YOUR_GEMINI_API_KEY>",
        "OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>"
      }
    }
  }
}

Set 4 environment variables before starting the server (below).Setup guides:Claude Code Cursor VS Code Claude Desktop

Darwin RAG MCP tools 11

Detected from the README

search_darwin
search_lists
get_search_results
get_search_result_by_id
get_schema
run_pipeline
purge_artifacts
create_store
list_files
file_status
get_logs

search_darwin	—
search_lists	—
get_search_results	—
get_search_result_by_id	—
get_schema	—
run_pipeline	—
purge_artifacts	—
create_store	—
list_files	—
file_status	—
get_logs	—

Configuration

ANTHROPIC_API_KEYSecret
Anthropic API key for LLM answer generation
GEMINI_API_KEYSecret
Google Gemini API key
OPENAI_API_KEYSecret
OpenAI API key for LLM answer generation
DARWIN_BASE_DIR
Override the base data directory

Name	Description
ANTHROPIC_API_KEY	Anthropic API key for LLM answer generation	Secret
GEMINI_API_KEY	Google Gemini API key	Secret
OPENAI_API_KEY	OpenAI API key for LLM answer generation	Secret
DARWIN_BASE_DIR	Override the base data directory

Automated checks

Ran Nov 12, 2026Full report →

100/100

Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work

Show this score in your README

Source repository linked and reachablePass
Open source license (OSI)Pass
Commit or release in the last yearPass
Package name not close to a popular packagePass
Remote endpoint uses HTTPSNot checked
Destructive tools are labelledNot checked
No hidden instructions to the modelPass
No critical advisory in the package or its dependenciesPass

README

View on GitHub

Darwin RAG

Search your own documents with any AI agent, privately, on your own machine.

One-time internet is needed to download models during setup. After that, search and indexing run fully offline.

Ingestion: PDF, Markdown, HTML, images (OCR), CSV, Excel, ODS, URLs
Indexing: BM25 keyword + dense embedding hybrid index with configurable chunking strategies
Search: Hybrid, semantic, or keyword retrieval with reranking, diversity rerank, and structural penalties
Generation: LLM-backed answer synthesis via LiteLLM (OpenAI, Anthropic, Gemini, etc.)
Observability: Structured logging with per-session history, queryable via MCP
Isolation: Multiple independent stores for tenant/project separation
Deployment: stdio (AI agent subprocess), SSE, or Streamable HTTP; Docker-ready
Local-first: Everything runs locally, fully offline-capable after setup

Built by BrightDotDev.

Why Darwin?

Private by default. Your documents stay on your machine.
Works with your agent. Standard MCP server: Claude Desktop, Cursor, and other MCP clients.
Search that fits the question. Keyword for exact terms, semantic for meaning, hybrid when unsure.
Light to start. The required preset downloads just one embedding model.

Quick Start

1. Install

pip install darwin-rag

2. Set up models

# Interactive: detects hardware, pick your models
darwin-admin setup interactive

# Or one-shot (embedding-only, no prompts)
darwin-admin setup --preset required

3. Start the MCP server & connect

# stdio mode: for AI agent subprocess (Claude Desktop, Cursor, etc.)
darwin mcp

# Or HTTP mode: for remote clients
darwin mcp --http --port 8765

Configure your MCP client:

{
  "mcpServers": {
    "darwin": {
      "command": "darwin",
      "args": ["mcp"],
      "env": {
        "OPENAI_API_KEY": "sk-..."  // At least one LLM provider key
      }
    }
  }
}

Or generate config automatically:

darwin config claude          # Claude Desktop config
darwin config cursor          # Cursor config
darwin config all --copy      # All clients + copy to clipboard

4. Try it

Ask your agent: "Ingest ./my-notes with Darwin, then find everything I wrote about ."

Use it as an agent skill

MCP Tools

Tool	Description
`search_darwin`	Query the knowledge base with hybrid/semantic/keyword search
`search_lists`	Search structured data (CSVs, JSON arrays) by field values
`get_search_results`	List saved search results
`get_search_result_by_id`	Load a saved search result by filename
`get_schema`	Inspect schemas for structured files (keys, types, record counts)
`run_pipeline`	Ingest + index documents from a path or URL
`purge_artifacts`	Delete pipeline artifacts for specific files
`create_store`	Create a new isolated data store
`list_files`	List all tracked files with pipeline status
`file_status`	Detailed status for a single file across all stages
`get_logs`	Query session logs (oldest first, INFO excluded)

Full documentation: docs/mcp.md

Remote / HTTP Mode

Start the server on a network-accessible endpoint:

# SSE transport (legacy)
darwin mcp --sse --host 0.0.0.0 --port 8765

# Streamable HTTP transport (recommended for production)
darwin mcp --http --host 0.0.0.0 --port 8765

Configure your MCP client with the URL:

{
  "mcpServers": {
    "darwin": {
      "url": "http://your-host:8765/mcp"  // or /sse for SSE mode
    }
  }
}

Environment Variables

Variable	Required	Description
`OPENAI_API_KEY`	No*	OpenAI provider key
`ANTHROPIC_API_KEY`	No*	Anthropic provider key
`GEMINI_API_KEY`	No*	Google Gemini provider key
`MISTRAL_API_KEY`	No*	Mistral AI provider key
`GROQ_API_KEY`	No*	Groq provider key
`COHERE_API_KEY`	No*	Cohere provider key
`TOGETHER_API_KEY`	No*	Together AI provider key
`OPENROUTER_API_KEY`	No*	OpenRouter provider key
`DEEPSEEK_API_KEY`	No*	DeepSeek provider key
`DARWIN_BASE_DIR`	No	Override the base data directory
`NO_COLOR`	No	Set to any value to disable ANSI color output

* At least one LLM provider key is required for answer generation. Search/indexing works without any.

Setup Details

Command	What it does
`darwin-admin setup interactive`	Guided setup: detect hardware, choose models
`darwin-admin setup --preset required`	Download embedding model only (fastest)
`darwin-admin setup --preset recommended`	Embedding + reranker + OCR models
`darwin-admin setup logging`	Reconfigure logging only
`darwin-admin setup validate`	Validate current setup

See docs/setup.md for the full walkthrough including Docker, from-source install, and API key configuration.

CLI Reference

darwin: User CLI

Command	Description
`darwin mcp`	Start MCP server (stdio, `--sse` or `--http` for network)
`darwin config [client]`	Generate MCP client config

darwin-admin: Power-user CLI

Command	Description
`darwin-admin setup`	Setup models, logging, and configuration
`darwin-admin status`	System status overview
`darwin-admin models`	Model registry: list, install, switch, keys
`darwin-admin store`	Data store: status, files, audit, health, repair
`darwin-admin pipeline`	Ingestion pipeline: run, ingest, index, purge
`darwin-admin search`	Interactive search
`darwin-admin logs`	Structured log viewer and management
`darwin-admin system`	System information
`darwin-admin uninstall`	Remove Darwin data and configuration

See docs/admin.md for the full command reference.

Python API

For embedding darwin-rag as a library in your own app:

from core import Darwin

d = Darwin()
d.ingest("./papers", recursive=True)
results = d.search("what is this paper about")
records = d.search_records(filters={"status": "active"})

Full reference: docs/api.md

Documentation

Doc	What
setup.md	Full setup walkthrough
mcp.md	MCP server, tools, resources, transports
admin.md	Admin CLI reference
architecture.md	For developers and contributors
pipeline.md	Ingestion & indexing
retrieval.md	Search engine
storage.md	DarwinStore
models.md	Model registry & inference
logger.md	Structured logging
orchestrators.md	High-level business logic
api.md	Python API (Darwin class)

Contributing

Found a bug? Want to add something? You're welcome here.

Issues: open one at github.com/BrightDotDev/DARWIN/issues
Code: fork, branch, PR. Keep it minimal.
AI-generated code is fine, but you own what you ship. Test it before submitting.

Read CONTRIBUTING.md for the full guidelines.

License

MIT. See LICENSE.

Core architecture and implementation by BrightDotDev.

Read full README

Darwin RAG MCP questions

How do I add Darwin RAG MCP to Claude Code?

How do I add Darwin RAG MCP to Cursor?

Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.

What tools does Darwin RAG MCP provide?

It exposes 11 tools, including search_darwin, search_lists, get_search_results, get_search_result_by_id, get_schema.

Does Darwin RAG work offline?

Yes, after an initial internet connection is used to download models during setup, all search and indexing operations run fully offline.

Is my data private?

Yes, Darwin is designed to be local-first, meaning your documents stay on your own machine rather than being sent to a cloud index.

Which AI clients can I use with Darwin?

It works with standard MCP clients such as Claude Desktop and Cursor.

Facts

Nov 13, 2026

Stars: 3
Downloads, 30 days: 310
Latest version: 0.2.18
Last commit: Oct 14, 2026
License: MIT
Transport: stdio
Package: darwin-rag

Brightdotdev ↗

Community publisher

Published by an independent maintainer.

Alternatives

Works with

Claude Code Cursor VS Code Claude Desktop Codex Gemini CLI Windsurf Devin

Badge for your README

Show your HostedMCP checks score. The badge links readers to install instructions for every client.

[![HostedMCP checks](https://api.hostedmcp.org/v1/badge/server/brightdotdev/darwin.svg)](https://hostedmcp.org/servers/brightdotdev/darwin/checks)

Maintainer?

Claim this listing to edit it and add the HostedMCP badge to your README.

Claim listing

Before you install

Servers run with the permissions you give them. Use the narrowest token or database role that does the job.

Darwin RAG MCP server

What is Darwin RAG MCP?

About Darwin RAG MCP server

What you can do with it

How to install Darwin RAG MCP

Install Darwin RAG MCP in Claude Code

Install Darwin RAG MCP in Cursor

Install Darwin RAG MCP in VS Code

Install Darwin RAG MCP in Claude Desktop

Install Darwin RAG MCP in Codex

Install Darwin RAG MCP in Gemini CLI

Darwin RAG MCP tools 11

Configuration

Automated checks

README

Darwin RAG

Why Darwin?

Quick Start

1. Install

2. Set up models

3. Start the MCP server & connect

4. Try it

Use it as an agent skill

MCP Tools

Remote / HTTP Mode

Environment Variables

Setup Details

CLI Reference

Python API

Documentation

Contributing

License

Darwin RAG MCP questions

Darwin RAG MCP server

What is Darwin RAG MCP?

About Darwin RAG MCP server

What you can do with it

How to install Darwin RAG MCP

Install Darwin RAG MCP in Claude Code

Install Darwin RAG MCP in Cursor

Install Darwin RAG MCP in VS Code

Install Darwin RAG MCP in Claude Desktop

Install Darwin RAG MCP in Codex

Install Darwin RAG MCP in Gemini CLI

Darwin RAG MCP tools 11

Configuration

Automated checks

README

Darwin RAG

Why Darwin?

Quick Start

1. Install

2. Set up models

3. Start the MCP server & connect

4. Try it

Use it as an agent skill

MCP Tools

Remote / HTTP Mode

Environment Variables

Setup Details

CLI Reference

Python API

Documentation

Contributing

License

Darwin RAG MCP questions