Search / io.github.Brightdotdev/darwin-rag
Darwin RAG
L0· runs locallyLocal-first RAG engine with MCP server for AI agent integration.
v0.2.18 · active · repository · descriptor JSON · versions
Search / io.github.Brightdotdev/darwin-rag
L0· runs locallyLocal-first RAG engine with MCP server for AI agent integration.
v0.2.18 · active · repository · descriptor JSON · versions
{
"mcpServers": {
"darwin-rag": {
"command": "uvx",
"args": [
"darwin-rag==0.2.18",
"mcp"
],
"env": {
"OPENAI_API_KEY": "${OPENAI_API_KEY}",
"ANTHROPIC_API_KEY": "${ANTHROPIC_API_KEY}",
"GEMINI_API_KEY": "${GEMINI_API_KEY}"
}
}
}
}claude mcp add darwin-rag -e "OPENAI_API_KEY=${OPENAI_API_KEY}" -e "ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY}" -e "GEMINI_API_KEY=${GEMINI_API_KEY}" -- uvx darwin-rag==0.2.18 mcp[mcp_servers.darwin-rag]
command = "uvx"
args = ["darwin-rag==0.2.18", "mcp"]
env = { "OPENAI_API_KEY" = "${OPENAI_API_KEY}", "ANTHROPIC_API_KEY" = "${ANTHROPIC_API_KEY}", "GEMINI_API_KEY" = "${GEMINI_API_KEY}" }
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"darwin-rag": {
"type": "local",
"command": [
"uvx",
"darwin-rag==0.2.18",
"mcp"
],
"enabled": true,
"environment": {
"OPENAI_API_KEY": "{env:OPENAI_API_KEY}",
"ANTHROPIC_API_KEY": "{env:ANTHROPIC_API_KEY}",
"GEMINI_API_KEY": "{env:GEMINI_API_KEY}"
}
}
}
}{
"mcpServers": {
"darwin-rag": {
"command": "uvx",
"args": [
"darwin-rag==0.2.18",
"mcp"
],
"env": {
"OPENAI_API_KEY": "${OPENAI_API_KEY}",
"ANTHROPIC_API_KEY": "${ANTHROPIC_API_KEY}",
"GEMINI_API_KEY": "${GEMINI_API_KEY}"
}
}
},
"deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=darwin-rag&config=eyJjb21tYW5kIjoidXZ4IiwiYXJncyI6WyJkYXJ3aW4tcmFnPT0wLjIuMTgiLCJtY3AiXSwiZW52Ijp7Ik9QRU5BSV9BUElfS0VZIjoiJHtPUEVOQUlfQVBJX0tFWX0iLCJBTlRIUk9QSUNfQVBJX0tFWSI6IiR7QU5USFJPUElDX0FQSV9LRVl9IiwiR0VNSU5JX0FQSV9LRVkiOiIke0dFTUlOSV9BUElfS0VZfSJ9fQ%3D%3D"
}{
"servers": {
"darwin-rag": {
"type": "stdio",
"command": "uvx",
"args": [
"darwin-rag==0.2.18",
"mcp"
],
"env": {
"OPENAI_API_KEY": "${OPENAI_API_KEY}",
"ANTHROPIC_API_KEY": "${ANTHROPIC_API_KEY}",
"GEMINI_API_KEY": "${GEMINI_API_KEY}"
}
}
}
}{
"mcpServers": {
"darwin-rag": {
"command": "uvx",
"args": [
"darwin-rag==0.2.18",
"mcp"
],
"env": {
"OPENAI_API_KEY": "${OPENAI_API_KEY}",
"ANTHROPIC_API_KEY": "${ANTHROPIC_API_KEY}",
"GEMINI_API_KEY": "${GEMINI_API_KEY}"
}
}
}
}extensions:
"darwin-rag":
enabled: true
name: "darwin-rag"
type: stdio
cmd: "uvx"
args:
- "darwin-rag==0.2.18"
- "mcp"
envs:
"OPENAI_API_KEY": "${OPENAI_API_KEY}"
"ANTHROPIC_API_KEY": "${ANTHROPIC_API_KEY}"
"GEMINI_API_KEY": "${GEMINI_API_KEY}"
timeout: 300
Placeholders to fill from your own secret store: ${OPENAI_API_KEY}, ${ANTHROPIC_API_KEY}, ${GEMINI_API_KEY}. The registry never accepts secret values.
This is a local package: the command runs on your machine.
Not scored: fewer than three checks apply, usually because no remote answered a credential-free probe or the server is a local package.
protocol.modern, protocol.stateless, protocol.transport, protocol.list_ttlno remote answered a protocol handshake (not probed yet, unreachable, or local-only)auth.prm, auth.as_metadata, auth.cimdno remote uses OAuthauth.secret_in_urlno templated URLtools.descriptions, tools.description_length, tools.schemas, tools.annotations, tools.directory_hints, tools.token_cost, tools.api_dumptool list unknown (behind auth, not probed, or empty)stability.changes, stability.rug_pulltool list unknowndeps.known_vulns3 advisories to act on (malicious, or rated high or critical with a fix available): GHSA-cq5v-8q36-5273 in [email protected] (indirect, fixed in 3.14.3), GHSA-4xpc-pv4p-pm3w in [email protected] (direct, fixed in 1.84.0), GHSA-7488-6r32-c95q in [email protected] (direct, fixed in 1.84.0); 15 more of lower severity or without a fixdeps.mcp_sdk_versionmcp 2.2.0, no known advisorydeps.resolvable[email protected] resolved: 174 packagesNo tool definition changes recorded. A server's first observation is its baseline; later probes record what changes.
Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.
+repository +namespace-matches-repo ~liveness-unmeasured ~updated-54d-ago
Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.
[email protected] PyPI173 dependencies, resolved · MCP SDK mcp 2.2.0 · advisories checked 2026-10-19
| advisory | severity | package | fixed in |
|---|---|---|---|
| GHSA-4xpc-pv4p-pm3wLiteLLM: Authentication Bypass via Host Header Injection | critical | [email protected]direct | fixed in 1.84.0 |
| GHSA-cq5v-8q36-5273AIOHTTP: Out-of-bounds heap read in C HTTP response parser error path (malformed chunked response) | high | [email protected]indirect | fixed in 3.14.3 |
| GHSA-7488-6r32-c95qLiteLLM: MCP Authentication Bypass via OAuth2 Passthrough Fallback | high | [email protected]direct | fixed in 1.84.0 |
| GHSA-4fvr-rgm6-gqmcaiohttp: HTTP/1 Pipelined Requests Queue Without Limit | moderate | [email protected]indirect | fixed in 3.14.1 |
| GHSA-63hw-fmq6-xxg2aiohttp: C HTTP Parser Bypasses max_line_size for Fragmented Lines | moderate | [email protected]indirect | fixed in 3.14.1 |
| GHSA-g3cq-j2xw-wf74aiohttp: Unread Compressed Request Bodies Bypass client_max_size During Cleanup | moderate | [email protected]indirect | fixed in 3.14.1 |
| GHSA-hg6j-4rv6-33pgAIOHTTP is vulnerable to cross-origin redirect with per-request cookies | moderate | [email protected]indirect | fixed in 3.14.0 |
| GHSA-hpj7-wq8m-9hgpaiohttp: DigestAuthMiddleware Applies Credentials to Cross-Origin Redirect Challenges | moderate | [email protected]indirect | fixed in 3.14.1 |
| GHSA-jg22-mg44-37j8AIOHTTP is Vulnerable to Deserialization of Untrusted Data | moderate | [email protected]indirect | fixed in 3.14.0 |
| GHSA-mfx4-hv73-q22vAIOHTTP: HTTP request smuggling via WebSocket upgrade | moderate | [email protected]indirect | fixed in 3.14.2 |
8 more advisories in the dependencies endpoint.
Dependency graphs from deps.dev; advisories from OSV.dev, including the GitHub Advisory Database and the PyPI Advisory Database; all CC BY 4.0. The graph is what a clean install of this version resolves today; nothing was installed or run. How it is checked.
| package | registry | version | runtime | secrets |
|---|---|---|---|---|
darwin-rag | pypi | 0.2.18 | – | OPENAI_API_KEY, ANTHROPIC_API_KEY, GEMINI_API_KEY |
No tools observed. Local packages are never executed by the registry.
Schemas: list_tools.
{
"name": "io.github.Brightdotdev/darwin-rag",
"title": "Darwin RAG",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"version": "0.2.18",
"packages": [
{
"version": "0.2.18",
"transport": {
"type": "stdio"
},
"identifier": "darwin-rag",
"registryType": "pypi",
"registryBaseUrl": "https://pypi.org",
"packageArguments": [
{
"type": "positional",
"value": "mcp"
}
],
"environmentVariables": [
{
"name": "OPENAI_API_KEY",
"isSecret": true,
"description": "OpenAI API key for LLM answer generation"
},
{
"name": "ANTHROPIC_API_KEY",
"isSecret": true,
"description": "Anthropic API key for LLM answer generation"
},
{
"name": "GEMINI_API_KEY",
"isSecret": true,
"description": "Google Gemini API key"
},
{
"name": "DARWIN_BASE_DIR",
"description": "Override the base data directory"
}
]
}
],
"repository": {
"url": "https://github.com/Brightdotdev/DARWIN",
"source": "github"
},
"description": "Local-first RAG engine with MCP server for AI agent integration."
}