repo-context-mcp

MCP server that helps AI coding agents understand a repository — without dumping the entire monorepo into the prompt.

Works with Codex, Claude Code, Cursor, Cline, and any client that speaks Model Context Protocol.

Why

AI agents waste tokens re-walking node_modules, missing entrypoints, or pasting random files. repo-context-mcp exposes three focused tools:

Local-only. No cloud. No telemetry. Stdio transport.

Related MCP server: codeweave-mcp

Install

# run from source
git clone https://github.com/nduc99911/repo-context-mcp.git
cd repo-context-mcp
npm install
npm run build

# or via npx (after publish)
npx -y repo-context-mcp

Requires Node.js 18+.

MCP client config

Claude Desktop / Claude Code

{
  "mcpServers": {
    "repo-context": {
      "command": "npx",
      "args": ["-y", "repo-context-mcp"],
      "env": {
        "REPO_CONTEXT_ROOT": "/absolute/path/to/your/repo"
      }
    }
  }
}

Cursor

Settings → MCP → add server with command npx and args ["-y", "repo-context-mcp"].

Codex / generic stdio

REPO_CONTEXT_ROOT=/path/to/repo node /path/to/repo-context-mcp/dist/server.js

From this repository after build:

npm run build
node dist/server.js

Optional env:

Each tool also accepts an explicit root argument.

Tools

repo_map

root?: string
max_depth?: number      # default 6
max_entries?: number    # default 400

Returns a markdown tree, file count, and likely entrypoints (package.json, README.md, src/index.ts, AGENTS.md, …). Skips node_modules, .git, dist, etc.

search_code

query: string
root?: string
max_results?: number    # default 50
case_sensitive?: boolean

Substring search across source-like extensions.

pack_context

root?: string
focus?: string[]        # keywords / path fragments to prioritize
max_tokens?: number     # default 12000 (approx)
max_files?: number      # default 40

Ranks files (entrypoints + focus matches), respects a rough token budget (~4 chars/token), and returns a single markdown document ready to paste into an agent prompt or PR review.

Library API

You can use the core without MCP:

import {
  buildRepoMap,
  formatRepoMap,
  searchCode,
  packContext,
} from "repo-context-mcp";

const map = buildRepoMap({ root: process.cwd() });
console.log(formatRepoMap(map));

const hits = searchCode({ root: process.cwd(), query: "TODO" });
const pack = packContext({
  root: process.cwd(),
  focus: ["auth"],
  maxTokens: 8000,
});
console.log(pack.markdown);

Demo (no MCP client)

npm install
npm test
npm run build

# map the sample tree
node --input-type=module -e "import { buildRepoMap, formatRepoMap } from './dist/index.js'; console.log(formatRepoMap(buildRepoMap({ root: 'examples/sample-repo' })));"

Security

• Reads files only under the requested root.

• Does not execute project code.

• Skips common vendor dirs and obvious binaries.

• Still: only point it at repositories you trust.

See SECURITY.md.

Project status

v0.1.0 — usable MCP server + library.

Roadmap:

• Optional ripgrep backend for large monorepos

• .gitignore native respect (beyond default ignore list)

• SARIF / JSON machine output modes

• GitHub Action: pack context on each PR

• Baseline symbol index (tree-sitter) for find_symbol

Contributing

See CONTRIBUTING.md.

npm install
npm test
npm run lint
npm run build

License

MIT © Nguyen Duc

Built as a real maintainer / agent-tooling utility for the MCP ecosystem — not a placeholder repo. Issues and PRs welcome.