MCP Hub
Back to servers

better-code-review-graph

Knowledge graph for token-efficient code reviews with fixed search and configurable embeddings

Registryglama
Stars
1
Forks
1
Updated
Mar 20, 2026

Quick Install

uvx better-code-review-graph

better-code-review-graph

mcp-name: io.github.n24q02m/better-code-review-graph

Knowledge graph for token-efficient code reviews -- fixed search, configurable embeddings, qualified call resolution.

CI codecov PyPI Docker License: MIT

Python MCP semantic-release Renovate

Fork of code-review-graph with critical bug fixes, configurable embeddings, and production CI/CD. Parses your codebase with Tree-sitter, builds a structural graph of functions/classes/imports, and gives Claude (or any MCP client) precise context so it reads only what matters.


Why Better

Featurecode-review-graphbetter-code-review-graph
Multi-word searchBroken (literal substring)AND-logic word splitting
callers_of/callees_ofEmpty results (bare name targets)Qualified name resolution + bare fallback
Embeddingsentence-transformers + torch (1.1 GB)qwen3-embed ONNX + LiteLLM (200 MB), dual-mode
Output sizeUnbounded (500K+ chars)Paginated (max_results, truncated flag)
Tool design9 individual tools3-tier: graph (mega) + config + help
Plugin hooksInvalid PostEdit/PostGitValid PostToolUse

All fixes are submitted upstream as standalone PRs (see Upstream PRs). If all are merged, this repo will be archived.


Installation

Claude Code

claude mcp add better-code-review-graph -- uvx --python 3.13 better-code-review-graph serve

Claude Code Plugin

claude plugin install n24q02m/better-code-review-graph@better-code-review-graph

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "better-code-review-graph": {
      "command": "uvx",
      "args": ["--python", "3.13", "better-code-review-graph", "serve"]
    }
  }
}

Codex (~/.codex/config.toml)

[mcp_servers.better-code-review-graph]
command = "uvx"
args = ["--python", "3.13", "better-code-review-graph", "serve"]

Gemini CLI (~/.gemini/settings.json)

{
  "mcpServers": {
    "better-code-review-graph": {
      "command": "uvx",
      "args": ["--python", "3.13", "better-code-review-graph", "serve"]
    }
  }
}

OpenCode (~/.opencode.json)

{
  "mcpServers": {
    "better-code-review-graph": {
      "command": "uvx",
      "args": ["--python", "3.13", "better-code-review-graph", "serve"]
    }
  }
}

Windsurf (~/.codeium/windsurf/mcp_config.json)

{
  "mcpServers": {
    "better-code-review-graph": {
      "command": "uvx",
      "args": ["--python", "3.13", "better-code-review-graph", "serve"]
    }
  }
}

Cline (cline_mcp_settings.json)

{
  "mcpServers": {
    "better-code-review-graph": {
      "command": "uvx",
      "args": ["--python", "3.13", "better-code-review-graph", "serve"]
    }
  }
}

Amp (~/.config/amp/settings.json)

{
  "mcpServers": {
    "better-code-review-graph": {
      "command": "uvx",
      "args": ["--python", "3.13", "better-code-review-graph", "serve"]
    }
  }
}

Docker

docker run -i --rm n24q02m/better-code-review-graph

pip

pip install better-code-review-graph
better-code-review-graph serve

Tools

graph -- Knowledge graph operations

Actions: build | update | query | search | impact | review | embed | stats | large_functions

ActionDescription
buildFull or incremental graph build. Set full_rebuild=true to re-parse all files.
updateAlias for build with full_rebuild=false (incremental).
queryRun predefined queries: callers_of, callees_of, imports_of, importers_of, children_of, tests_for, inheritors_of, file_summary.
searchSearch code entities by name/keyword or semantic similarity.
impactBlast radius of changed files. Auto-detects from git diff. Paginated with max_results.
reviewToken-optimized review context with structural summary, source snippets, and review guidance.
embedCompute vector embeddings for semantic search. Dual-mode: local ONNX or cloud LiteLLM.
statsGraph size, languages, node/edge breakdown, embedding count.
large_functionsFind functions/classes exceeding a line-count threshold.

config -- Server configuration

Actions: status | set | cache_clear

ActionDescription
statusServer info: version, graph path, node/edge counts, embedding backend.
setUpdate runtime settings (e.g., log_level).
cache_clearRemove all computed embeddings.

help -- Full documentation

Topics: graph | config

Returns complete documentation for each tool. Use when the compressed descriptions above are insufficient.


Embedding Backends

BackendConfigSizeDescription
local (default)Nothing needed~570 MB (first use)qwen3-embed ONNX. Zero-config.
litellmAPI_KEYS or LITELLM_PROXY_URL0 MBCloud providers via LiteLLM.
  • Auto-detection: API_KEYS or LITELLM_PROXY_URL set -> LiteLLM. Otherwise -> local ONNX.
  • Override: EMBEDDING_BACKEND=local or EMBEDDING_BACKEND=litellm.
  • Fixed 768-dim storage: Switching backends does NOT invalidate existing vectors.

Configuration

VariableDefaultDescription
EMBEDDING_BACKEND(auto-detect)local or litellm
EMBEDDING_MODELgemini/gemini-embedding-001LiteLLM model (when backend=litellm)
API_KEYS-LLM API keys (format: ENV_VAR:key,...). Enables LiteLLM.
LITELLM_PROXY_URL-LiteLLM Proxy URL. Enables LiteLLM via proxy.
LITELLM_PROXY_KEY-LiteLLM Proxy virtual key.

Ignore files

Create .code-review-graphignore in your project root:

generated/**
*.generated.ts
vendor/**
node_modules/**

Supported Languages

Python, TypeScript, JavaScript, Go, Rust, Java, C#, Ruby, Kotlin, Swift, PHP, C/C++


Upstream PRs

All fixes are submitted to code-review-graph:

  • #37 -- Multi-word search AND logic
  • #38 -- Parser call target resolution (fixes #20)
  • #39 -- Impact radius output pagination

If all upstream PRs are merged, this repository will be archived.


Build from Source

git clone https://github.com/n24q02m/better-code-review-graph
cd better-code-review-graph
uv sync --group dev
uv run pytest
uv run better-code-review-graph serve

Requirements: Python 3.13, uv


Compatible With

Claude Desktop Claude Code Cursor VS Code Copilot Antigravity Gemini CLI OpenAI Codex OpenCode

Also by n24q02m

ServerDescriptionInstall
wet-mcpWeb search, content extraction, library docsuvx --python 3.13 wet-mcp@latest
mnemo-mcpPersistent AI memory with hybrid searchuvx mnemo-mcp@latest
better-notion-mcpNotion API for AI agentsnpx -y @n24q02m/better-notion-mcp@latest
better-email-mcpEmail (IMAP/SMTP) for AI agentsnpx -y @n24q02m/better-email-mcp@latest
better-godot-mcpGodot Engine for AI agentsnpx -y @n24q02m/better-godot-mcp@latest
better-telegram-mcpTelegram Bot API + MTProto for AI agentsuvx --python 3.13 better-telegram-mcp@latest

License

MIT - See LICENSE

Reviews

No reviews yet

Sign in to write a review