Crg

io.github.n24q02m/crg · v3.32.0

Token-efficient code review knowledge graph: semantic search and call-graph resolution.

Source code Set it up

Connect Runs on your machine

Terminal

claude mcp add crg -e EMBEDDING_MODELS=<EMBEDDING_MODELS> -e LOCAL_EMBEDDING_MODEL=<LOCAL_EMBEDDING_MODEL> -e LOCAL_RERANK_MODEL=<LOCAL_RERANK_MODEL> -e LOCAL_EMBEDDING_DIM=<LOCAL_EMBEDDING_DIM> -e LOCAL_EMBEDDING_MODEL_FILE=<LOCAL_EMBEDDING_MODEL_FILE> -e LOCAL_EMBEDDING_POOLING=<LOCAL_EMBEDDING_POOLING> -e LOCAL_EMBEDDING_NORMALIZE=<LOCAL_EMBEDDING_NORMALIZE> -e HULL_EMBED_API_KEY=<HULL_EMBED_API_KEY> -e HULL_CHAT_API_KEY=<HULL_CHAT_API_KEY> -e EMBEDDING_BACKEND=<EMBEDDING_BACKEND> -- uvx n24q02m-crg==3.32.0

claude_desktop_config.json

{
  "mcpServers": {
    "crg": {
      "command": "uvx",
      "args": [
        "n24q02m-crg==3.32.0"
      ],
      "env": {
        "EMBEDDING_MODELS": "<EMBEDDING_MODELS>",
        "LOCAL_EMBEDDING_MODEL": "<LOCAL_EMBEDDING_MODEL>",
        "LOCAL_RERANK_MODEL": "<LOCAL_RERANK_MODEL>",
        "LOCAL_EMBEDDING_DIM": "<LOCAL_EMBEDDING_DIM>",
        "LOCAL_EMBEDDING_MODEL_FILE": "<LOCAL_EMBEDDING_MODEL_FILE>",
        "LOCAL_EMBEDDING_POOLING": "<LOCAL_EMBEDDING_POOLING>",
        "LOCAL_EMBEDDING_NORMALIZE": "<LOCAL_EMBEDDING_NORMALIZE>",
        "HULL_EMBED_API_KEY": "<HULL_EMBED_API_KEY>",
        "HULL_CHAT_API_KEY": "<HULL_CHAT_API_KEY>",
        "EMBEDDING_BACKEND": "<EMBEDDING_BACKEND>"
      }
    }
  }
}

~/.cursor/mcp.json

{
  "mcpServers": {
    "crg": {
      "command": "uvx",
      "args": [
        "n24q02m-crg==3.32.0"
      ],
      "env": {
        "EMBEDDING_MODELS": "<EMBEDDING_MODELS>",
        "LOCAL_EMBEDDING_MODEL": "<LOCAL_EMBEDDING_MODEL>",
        "LOCAL_RERANK_MODEL": "<LOCAL_RERANK_MODEL>",
        "LOCAL_EMBEDDING_DIM": "<LOCAL_EMBEDDING_DIM>",
        "LOCAL_EMBEDDING_MODEL_FILE": "<LOCAL_EMBEDDING_MODEL_FILE>",
        "LOCAL_EMBEDDING_POOLING": "<LOCAL_EMBEDDING_POOLING>",
        "LOCAL_EMBEDDING_NORMALIZE": "<LOCAL_EMBEDDING_NORMALIZE>",
        "HULL_EMBED_API_KEY": "<HULL_EMBED_API_KEY>",
        "HULL_CHAT_API_KEY": "<HULL_CHAT_API_KEY>",
        "EMBEDDING_BACKEND": "<EMBEDDING_BACKEND>"
      }
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "crg": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "n24q02m-crg==3.32.0"
      ],
      "env": {
        "EMBEDDING_MODELS": "<EMBEDDING_MODELS>",
        "LOCAL_EMBEDDING_MODEL": "<LOCAL_EMBEDDING_MODEL>",
        "LOCAL_RERANK_MODEL": "<LOCAL_RERANK_MODEL>",
        "LOCAL_EMBEDDING_DIM": "<LOCAL_EMBEDDING_DIM>",
        "LOCAL_EMBEDDING_MODEL_FILE": "<LOCAL_EMBEDDING_MODEL_FILE>",
        "LOCAL_EMBEDDING_POOLING": "<LOCAL_EMBEDDING_POOLING>",
        "LOCAL_EMBEDDING_NORMALIZE": "<LOCAL_EMBEDDING_NORMALIZE>",
        "HULL_EMBED_API_KEY": "<HULL_EMBED_API_KEY>",
        "HULL_CHAT_API_KEY": "<HULL_CHAT_API_KEY>",
        "EMBEDDING_BACKEND": "<EMBEDDING_BACKEND>"
      }
    }
  }
}

Replace the values in angle brackets with your own. Keys stay on your machine; we never see them.

Tools

This server runs locally, so its tools are listed by your MCP client once it starts.

Environment variables

Name	Description
`EMBEDDING_MODELS` Optional	Embedding models in selection order; the current runtime uses the first provider/model entry; empty = local ONNX
`LOCAL_EMBEDDING_MODEL` Optional	Built-in fastretrieval model ID or local directory with fastretrieval-manifest.json
`LOCAL_RERANK_MODEL` Optional	Fastretrieval TextCrossEncoder model ID; empty = reranking disabled
`LOCAL_EMBEDDING_DIM` Optional	Required positive output dimension for an external local embedding ID without a manifest
`LOCAL_EMBEDDING_MODEL_FILE` Optional	ONNX file path inside a manifest-backed local embedding directory
`LOCAL_EMBEDDING_POOLING` Optional	Explicit pooling for an external local embedding ID without a manifest
`LOCAL_EMBEDDING_NORMALIZE` Optional	Explicit L2 normalization for an external local embedding ID without a manifest
`HULL_EMBED_API_KEY` Optional, secret	API key for the [models.embed] cell transport (OpenRouter pre-wired default); host-injected, overrides the cell api_key
`HULL_CHAT_API_KEY` Optional, secret	API key for the [models.chat] cell transport (OpenRouter pre-wired default); host-injected, enables LLM summaries when the cell model is set
`EMBEDDING_BACKEND` Optional	DEPRECATED (honored one release): embedding backend override 'local' or 'cloud'. Use EMBEDDING_MODELS instead.

Details

Package	`[email protected]` (PYPI, stdio)
First published	12 Nov 2026
Last updated	12 Nov 2026
Registry name	`io.github.n24q02m/crg`

More search and web servers See all

Live status

Local install

Installed and run on your own machine, so there is no public endpoint to check.

Pair it with live search

Agents that use Crg often also need current facts. NestDaddy MCP gives your AI today's internet: web search, real-time breaking news and full page reading in one connector.

See NestDaddy MCP

For maintainers

[![NestDaddy MCP](https://nestdaddy.com/mcp/servers/io-github-n24q02m-crg/badge.svg)](https://nestdaddy.com/mcp/servers/io-github-n24q02m-crg)

Add the badge to your README. It turns green while your server passes our daily check. Listing details come from the official MCP registry; update them there.

Listing data from the official MCP registry. Status and tools from NestDaddy's daily check. Browse all MCP servers.