Repo Cartographer MCP server

repo-cartographer

Understand any codebase in 60 seconds. An MCP server that turns any repository into an architecture diagram.

Point your LLM at a folder and get back an architecture map: languages, frameworks, entry points, modules, and an import graph — rendered as a Mermaid diagram you can drop into a PR, a doc, or an onboarding guide.

It is model-agnostic. It speaks the Model Context Protocol over stdio, so it works with Claude Code, Claude Desktop, Cursor, Cline, Copilot, or the OpenAI Agents SDK — no Claude-specific dependency.

Why it's different

The server extracts hard facts. The model does the reasoning.

repo-cartographer never tries to "understand" your code semantically. It parses deterministic facts — file tree, import edges, manifests, framework detection, entry points — and hands your LLM structured JSON plus a draft diagram. Your model turns those facts into the final narrative and a refined diagram.

That split keeps the server small, fast, testable, and portable — and it means the diagram is grounded in what's actually in the repo, not hallucinated.

Example output

Running generatediagram against this repo** produces (a draft the model then refines):

flowchart TD
    n0["src · 2 files"]
    n1["src/lib · library code · 9 files"]
    n2["src/resources · resource handlers · 1 file"]
    n3["src/tools · tool implementations · 4 files"]
    n0 --> n1
    n0 --> n2
    n0 --> n3
    n1 --> n0
    n3 --> n0
    n3 --> n1

A self-contained, shareable HTML render is committed under examples/ (both a high-level and a file-level detail view).

Install & run

Requires Node.js 18+.

# Run directly (no install)
npx -y repo-cartographer

# …or from source
git clone https://github.com/builditwithgk/repo-cartographer
cd repo-cartographer
npm install
npm run build
node dist/index.js

The server communicates over stdio; AI clients launch it that way. You can also use it directly from a terminal — see below.

Command line (no AI needed)

The same binary is dual-mode: with no arguments it's the MCP server; with a subcommand it's a plain CLI for humans and CI.

# Draw a diagram — path in, architecture.html out
npx -y repo-cartographer map ./my-project
npx -y repo-cartographer map ./my-project --level detail -o docs/architecture
npx -y repo-cartographer map ./my-project --format dot   # Graphviz DOT instead of Mermaid

# Enforce architecture rules (exits 1 on an error-level violation — use it in CI)
npx -y repo-cartographer check ./my-project --config .cartographer.yml

Zip-friendly: if you point it at an extracted "Download ZIP" folder (repo-main/ wrapper and all), it detects the wrapper and maps the real repo root — noted in the output, never silent.

Two output notations, one strategy: Mermaid because that's where people read it (GitHub renders it natively in PR comments and READMEs), DOT because that's what their tools eat (pipe it into Graphviz, Backstage, or anything else: dot -Tsvg architecture.dot). Both come with the same shareable HTML page and role-colored modules. When the repo has a .cartographer.yml, its diagram: section supplies the defaults for --level, --format and -o; explicit flags always win.

Shortened. The full README is on GitHub.