Get This Tool
Code Review Graph
Pricing
- Model
- Free
Summary
Your AI coding assistant is reading entire files when you ask about a three-line change — burning context window on code that has nothing to do with the diff. code-review-graph gives MCP-compatible tools the structural map they need to read only what changed and trace exactly what breaks downstream.
The tool builds a dependency graph of your codebase locally, then exposes that graph through MCP so Claude Code, Cursor, or any compatible assistant can ask targeted questions: which files are affected by this change, what is the impact radius, which communities cluster around this module. For large monorepos, this is the difference between a useful review context and a truncated one. The analysis runs entirely on your machine — no source code leaves the environment. The gap shows up when you need deep semantic understanding beyond structural imports; graph topology tells you what calls what, not whether the logic is correct.
Bottom line: Use this when your monorepo is silently degrading your AI assistant's review quality by flooding its context with unrelated files — but expect to pair it with a semantic layer if you need answers about intent, not just structure.
Community Performance Report Card
No community ratings yet. Be the first to rate this tool!
Community Benchmarks Community
Sign in to submit a benchmarkNo community benchmarks yet. Be the first to share a real-world data point.
Pros
Sign in to edit- Reads only changed files and their structural dependencies rather than entire repositories, so your AI assistant's context window goes toward relevant code instead of noise from unrelated modules.
- Impact radius scoring on change analysis, so reviewers see which downstream files carry the highest risk before opening a single one — rather than manually tracing imports across a large graph.
- Fully local execution with no cloud dependency, so source code never leaves the environment — a hard requirement for teams under data residency or confidentiality constraints.
- MIT-licensed with no paid tier and pip installation, so there is no procurement gate, no usage cap, and no feature that unlocks only when you upgrade.
- Unified graph model across multiple languages, so a polyglot monorepo gets consistent structural queries without separate tooling per language stack.
Cons
Sign in to edit- The graph captures import and call structure, not runtime behavior or semantic intent — questions like 'does this change break business logic in the billing module' return no useful answer, and teams with that requirement add a dedicated semantic search tool, maintaining two systems in parallel.
- MCP is the only consumption interface; development environments without MCP support get nothing from this tool. Teams using IDE plugins or assistants that do not expose MCP cannot integrate it without building a custom bridge.
- Community detection and architecture overview queries return structural clusters, which require a developer to interpret the output against domain knowledge — for teams onboarding to an unfamiliar codebase, the graph answers 'what talks to what' but not 'why.' Teams that need the 'why' typically switch to tools that ingest documentation and comments alongside the dependency graph.
Community Reviews
Sign in to write a reviewNo reviews yet. Be the first to share your experience.
About
- Platforms
- Linux, macOS, Windows (Python 3.10+)
- API Available
- Yes
- Self-Hosted
- Yes
- Last Updated
- 2026-06-09T05:32:12.590Z
Best For
Who it's for
- Teams using Claude Code, Cursor, or other MCP-compatible AI coding assistants
- Large codebases where context window optimization is critical
- Projects requiring local-first code analysis without cloud dependencies
- Developers wanting risk-scored change impact analysis before review
- Multi-language codebases needing unified structural understanding
What it does well
- Large monorepos where the graph excludes thousands of files from review context and reads only affected files
- Code review: detect changes and get review context instead of reading entire files
- Understanding impact: get impact radius instead of manually tracing imports
- Architecture questions: get architecture overview and list communities
- Integration with AI coding tools for token-efficient pair programming
Integrations
Discussion Community
Sign in to commentNo discussion yet. Sign in to start the conversation.
Compare Code Review Graph
Spotted incorrect or missing data? Join our community of contributors.
Sign Up to ContributeCommunity Notes & Tips Community
Sign in to contributeBe the first to contribute. General notes, observations, gotchas, and tips from people who use this tool day-to-day.
Frequently Asked Questions
- Is Code Review Graph free?
- Yes — Code Review Graph is fully free to use. There is no paid tier.
- Is Code Review Graph open source?
- Yes. Code Review Graph is open source.
- Does Code Review Graph have an API?
- Yes. Code Review Graph exposes a developer API. See the official documentation at https://code-review-graph.com for details.
- Can I self-host Code Review Graph?
- Yes. Code Review Graph supports self-hosting on your own infrastructure.
- When was Code Review Graph released?
- Code Review Graph was first released in 2023.
- What platforms does Code Review Graph support?
- Code Review Graph is available on: Linux, macOS, Windows (Python 3.10+).
Hours Saved & ROI Stories Community
Sign in to contributeBe the first to contribute. Concrete time/cost savings, with context. e.g. "Cut my code review backlog from 4h to 45m per week."
Curated lists that include this category
AI coding assistants default to reading whole files because they have no other way to know which parts matter. code-review-graph builds a local dependency graph from your source code and surfaces it through the Model Context Protocol, so when an assistant asks about a change, it retrieves only the affected files and their structural relationships — not the entire repository. The core workflow is: install via pip, point it at your codebase, and the MCP server answers queries about change impact, import graphs, community clustering, and architecture overview on demand.
The differentiating capability is risk-scored change impact analysis. Rather than returning a flat list of files that import the changed module, the tool produces an impact radius — a scored view of how far a change propagates through the dependency graph. For teams doing pre-review triage, this surfaces the high-risk files before a reviewer opens anything.
The tool fits teams running Claude Code, Cursor, or other MCP-compatible assistants against codebases large enough that context window exhaustion is a real constraint, not a hypothetical one. It supports multiple languages under a unified graph model, so polyglot repositories get the same structural queries without per-language configuration overhead. The wall appears when a question requires understanding runtime behavior or business logic — the graph describes structure, and structure alone does not explain whether a dependency matters semantically. Teams with that requirement add a separate semantic search layer alongside this tool.
Installation is via pip from PyPI; the source is publicly available under MIT license on GitHub. There is no cloud component and no paid tier — the full capability is available locally from the first install. Integration requires an MCP-compatible host; tools without MCP support cannot consume the server’s output.