mcp-repo-graph 0.4.18

MCP server that gives LLMs a structural map of any codebase — entities, relationships, and flows — so they navigate to the right files without reading everything first.

repo-graph

Structural graph memory for AI coding assistants. Map your codebase. Navigate by structure. Read only what matters.

repo-graph gives LLMs a map of your codebase — entities, relationships, and flows — so they can navigate to the right files without reading everything first.

Instead of flooding an LLM's context window with your entire codebase (or hoping it guesses right), repo-graph builds a lightweight graph of what exists, how things connect, and where the entry points are. The LLM queries the graph, finds the minimal set of files it needs, and reads only those.

Demo

https://github.com/user-attachments/assets/a1e4171b-b225-40d4-9210-39453e14b76a

https://github.com/user-attachments/assets/fc3191e5-fc35-4bd7-8372-72af55995883

Same bug, same model, same prompt — the only difference is whether repo-graph is installed.

The task: fix a reversed comparison operator in a Go + Angular monorepo (566 nodes, 620 edges).

	Without repo-graph	With repo-graph
Tokens used	75,308	29,838
Time to fix	4m 36s	~30s
Files explored	~15 (grep, read, grep, read...)	2 (flow lookup + handler file)
Outcome	Found and fixed the bug	Found and fixed the bug

2.5x fewer tokens. ~9x faster. Same correct fix.

How the test was run

Both runs used identical conditions to keep the comparison fair:

• Same model: Claude Opus, 100% (no Haiku routing)
• Same prompt: "Groups that were created recently are showing as closed, and old groups show as open. This is backwards — new groups should be open for members to join. Find and fix the bug."
• Fresh context: each run started from /clear with no prior conversation
• No other tools: CLAUDE.md, plugins, hooks, and all other MCP servers were removed for both runs — the only variable was whether repo-graph was installed
• No hints: the prompt describes the symptom, not the location — Claude has to find group_controller.go:57 on its own

Without repo-graph, Claude greps for keywords, reads files, greps again, reads more files, and eventually narrows down to the bug. With repo-graph, Claude calls flow("groups"), gets back the exact handler function and file, reads it, and fixes it.

Browse pre-generated examples for FastAPI, Gin, Hono, and NestJS — real graph output you can inspect without installing anything.

The problem

LLMs working on code waste most of their context on orientation:

• Reading files that turn out to be irrelevant
• Missing connections between components in different languages
• Not knowing where a feature starts or what it touches
• Loading 50 files when 5 would do

This is expensive, slow, and gets worse as codebases grow.

How repo-graph solves it

repo-graph scans your codebase once and builds a graph of:

• Entities: modules, packages, classes, functions, routes, services, components
• Relationships: imports, calls, handles, defines, contains, cross-stack HTTP
• Flows: end-to-end paths from entry point to data layer

Then it exposes 11 MCP tools that let the LLM:

1. Orient — "What languages are in this repo? What are the main features?"
2. Navigate — "Trace the login flow from route to database" / "What's the shortest path between UserService and the payments API?"
3. Scope — "How many lines would I need to read to understand this feature?" / "Give me just the files I need for this bug fix"
4. Assess — "What's the blast radius of changing this function?" / "Which files are the biggest maintenance risks?"

The LLM gets structural context in a few hundred tokens instead of reading thousands of lines.

Supported languages

Language	Detection	What it extracts
Go	go.mod	Packages, functions, HTTP routes (gin/echo/chi/stdlib), imports
Rust	Cargo.toml	Crates, modules, structs, traits, functions, routes (Actix/Rocket/Axum)
TypeScript	tsconfig.json / package.json	Modules, classes, functions, import relationships
React	react in package.json	Components, hooks, context providers, React Router routes, fetch/axios calls, flows
Angular	@angular/core in package.json	Components, services, guards, DI injection, HTTP calls, feature flows
Vue	vue in package.json	SFCs, composables, Vue Router routes, fetch/axios calls
Python	pyproject.toml / setup.py / requirements.txt	Packages, modules, classes, functions, routes (Flask/FastAPI/Django)
Java/Kotlin	pom.xml / build.gradle	Packages, classes, routes (Spring/JAX-RS/Ktor/WebFlux/Micronaut)
Scala	build.sbt	Packages, objects/classes/traits, routes (Play/Akka HTTP/http4s)
Clojure	project.clj / deps.edn	Namespaces, defn/defprotocol/defrecord, routes (Compojure/Reitit)
C#/.NET	.csproj / .sln	Namespaces, classes, routes (ASP.NET/Minimal API)
Ruby	Gemfile / .gemspec	Files, classes, modules, Rails routes
PHP	composer.json	Namespaces, classes, interfaces, routes (Laravel/Symfony)
Swift	Package.swift / .xcodeproj	Files, types (class/struct/enum/protocol/actor), Vapor routes
C/C++	CMakeLists.txt / Makefile / meson.build	Sources, headers, classes, structs, enums, namespaces, includes
Dart/Flutter	pubspec.yaml	Modules, classes, widgets, go_router/shelf routes
Elixir/Phoenix	mix.exs	Modules, functions, Phoenix router scopes + routes
Solidity	.sol files / foundry.toml / hardhat.config.*	Contracts, interfaces, libraries, events, inheritance
Terraform	.tf files	Modules, resources, variables, outputs, module sources
SCSS	.scss files present	File-level bloat analysis

Cross-cutting extractors (work across all languages):

• Data sources — DB/cache/queue/blob/search/email client detection
• CLI entrypoints — Python click, JS commander/yargs, Go cobra, Rust clap
• gRPC — service/method definitions from .proto files
• Queue consumers — Celery, Dramatiq, BullMQ, Sidekiq, Oban, NATS
• Cross-stack HTTP — frontend fetch/axios calls linked to backend routes

Multiple languages can match one repo (e.g., Go backend + Angular frontend + SCSS). Each contributes its nodes and edges into a single unified graph.

Install

The package name is the run command — uvx mcp-repo-graph just works. No prior pip install, nothing to keep on PATH. This is the same command VS Code, Cursor, and the MCP registry use under the hood.

Requirements: Python 3.11+, and uv if you use the uvx path. Prebuilt wheels ship for the Rust engine on Linux (x86_64, aarch64), macOS (Intel + Apple Silicon), and Windows (x86_64) — no Rust toolchain needed.

Claude Code

claude mcp add repo-graph -- uvx mcp-repo-graph --repo .

(--repo . points the graph at the current project; use an absolute path to pin it.)

VS Code

One command — adds the server to your user config:

code --add-mcp '{"name":"repo-graph","command":"uvx","args":["mcp-repo-graph","--repo","${workspaceFolder}"]}'

Or click Install on the MCP gallery entry, or add it to .vscode/mcp.json manually (see below).

Cursor / any MCP client — manual config

Add this to your client's MCP config (.mcp.json, .cursor/mcp.json, .vscode/mcp.json, or ~/.claude.json):

{
  "mcpServers": {
    "repo-graph": {
      "command": "uvx",
      "args": ["mcp-repo-graph", "--repo", "/path/to/your/project"]
    }
  }
}

Prefer a persistent install? pip install mcp-repo-graph (or uv tool install mcp-repo-graph) puts a mcp-repo-graph / repo-graph command on your PATH; then use "command": "mcp-repo-graph" in the config above.

--repo also accepts a git URL. Point it at any public repo without cloning first — it shallow-clones and maps it (requires git):

uvx mcp-repo-graph --repo https://github.com/org/repo

Quick start

1. Initialise the target repo (optional)

uvx --from mcp-repo-graph repo-graph-init --repo /path/to/your/project
# or, if installed:  repo-graph-init --repo /path/to/your/project

This generates the graph, writes .mcp.json and CLAUDE.md instructions, and gets your AI assistant ready to use repo-graph. If you used the one-liners above, you can skip this — the server builds the graph on first connect.

2. Use it

The AI assistant now has access to all 11 tools. Example queries it can answer:

• "What does this codebase do?" → status tool
• "Trace the checkout flow" → flow tool
• "What would break if I change UserService?" → impact tool
• "Which nodes are relevant to this bug?" → activate / find tools
• "Give me the full graph context cheaply" → dense_text tool
• "Show me the auth flow visually" → graph_view tool

3. Keep it fresh with a git hook (recommended)

The graph auto-refreshes on cold start whenever the source tree has changed since the cached .gmap was written, so it's never stale when your assistant connects. To pre-warm the cache on every commit instead — so even the first query is instant — add a pre-commit hook:

# .git/hooks/pre-commit (or add to your existing hook)
#!/bin/sh
uvx --from mcp-repo-graph repo-graph-init --repo .   # or: repo-graph-init --repo .
git add .ai/repo-graph/

chmod +x .git/hooks/pre-commit

Every commit keeps the graph current. The LLM always has a fresh map without wasting a single token on generate.

Tip: If you don't want graph data in version control, add .ai/repo-graph/ to .gitignore and skip the git add line — the graph will just live locally.

MCP tools reference

repo-graph exposes 11 tools across four tiers.

Generation

Tool	Parameters	Description
generate	repo_path (optional)	Scan the codebase with tree-sitter, rebuild the graph, run cross-stack resolvers, and cache it

Navigation

Tool	Parameters	Description
status	(none)	Repo overview: node/edge counts, detected kinds, entry points, dense preview. Call this first to orient
flow	feature	End-to-end flow for a feature — entry point → service layer → data store, in layered tiers
trace	from_node, to_node	Shortest path between two nodes, hop by hop with tier transitions
impact	node, direction (downstream/upstream), depth	Blast radius — what a node affects (downstream) or depends on (upstream)
neighbours	node	All direct connections to and from a node, one hop each way

Activation & context

Tool	Parameters	Description
activate	seeds, top_k	Spreading activation (Personalized PageRank) from seed nodes — the most relevant nodes to your seeds
find	query	Find nodes by name or qualified-name pattern
dense_text	(none)	The full graph in dense sigil notation — the primary context tool; feed it to the LLM to navigate without reading files

Health & admin

Tool	Parameters	Description
graph_view	node (optional), depth	Visual ASCII map — a node's tree/neighbourhood, or the full overview
reload	(none)	Re-generate the graph from source after code changes

How it works

mcp-repo-graph is a thin Python MCP server that wraps glia, a Rust engine.

1. Parse — per-language tree-sitter parsers extract raw nodes and unresolved references
2. Extract — cross-cutting extractors layer on HTTP routes, data sources, CLI entrypoints, gRPC services, queue consumers
3. Resolve — graph builder resolves intra-repo references; cross-graph resolvers link stacks (frontend HTTP calls → backend routes, etc.)
4. Store — merged graph lands in .ai/repo-graph/ as a zero-copy .gmap (rkyv + mmap) plus JSON projections for portability
5. Serve — the MCP server loads the graph into memory and exposes the 11 tools

The Rust engine lives in its own glia repo; mcp-repo-graph is the MCP-facing thin wrapper.

Config (optional escape hatch)

If auto-detection misses a weird layout, drop .ai/repo-graph/config.yaml in the target repo:

skip:
  - legacy       # directory basenames excluded from the walk
  - scratch

roots:           # explicit roots heuristics miss — added on top of auto-detection
  - path: apps/weird-layout
    kind: python
  - path: services/custom
    kind: go

kind values: go, rust, python, typescript, react, vue, angular, java, scala, clojure, csharp, ruby, php, swift, c_cpp, dart, elixir, solidity, terraform. config.json works too if you prefer.

Graph data format

Generated files live in .ai/repo-graph/ inside the target repo:

• nodes.json — [{id, type, name, file_path, confidence, ...}, ...]
• edges.json — [{from, to, type}, ...]
• flows/*.yaml — named feature flows with ordered step sequences and kind (http/page/cli/grpc/queue)
• state.md — human-readable snapshot for quick orientation

Common edge types: imports, defines, contains, uses, calls, handles, handled_by, exports, includes, tests, cross-stack HTTP links.

Privacy Policy

repo-graph runs on your machine and is built to keep your code there. Full text: PRIVACY.md.

• Telemetry / analytics: None. No tracking, no update checks, no phone-home.
• Data collection & sharing: None. Your source code and graph data are never sent to repo-graph, its author, or any third party.
• Local processing & storage: Scanning and graph-building happen locally; the graph is cached in your project's .ai/repo-graph/ directory and stays on your device.
• Network access — only two cases, both user-initiated:
  1. Installation — uvx/pip downloads the package and its prebuilt engine wheel from PyPI.
  2. Git-URL targets — if you pass a git URL to --repo, repo-graph runs git clone against the URL you specified; nothing is sent to repo-graph or its author. A local --repo path (the default) makes zero network calls.
• Data retention: The local cache persists until you delete it — fully under your control.
• Contact: GitHub issues

License

MIT

Support

If repo-graph saved you time, consider buying me a coffee.

buymeacoffee.com/polycrisis