repo-map
A navigable symbol map of your codebase for coding agents, enabling efficient code navigation and reading only relevant symbols instead of entire files.
README
repo-map
A navigable map of your codebase for coding agents — so they stop reading whole files just to find their bearings.
repo-map is a Model Context Protocol (MCP) server. It parses a repository into a symbol graph, ranks every symbol by importance (a tuned PageRank), and exposes a handful of tools that let an agent like Claude Code locate code and read only the symbol it needs — instead of loading entire files to orient itself.
Think of it as an "Obsidian for your codebase": an outline + a reference graph + an importance sort, queryable without opening the files.
Why
Reading whole files to understand where a piece of logic lives is the single biggest source of wasted context in agentic coding. On a real exploration workflow over an unfamiliar Python repo, routing that navigation through repo-map instead of raw file reads measured:
| Metric | Result |
|---|---|
| Total workflow token cost | −33 % (up to −52 % cold) |
| Context loaded into the model | −64 % |
outline vs a full file read |
−96 % |
The gains come from never paying for a file body you don't end up editing.
Tools
| Tool | What it does |
|---|---|
index(path) |
(Re)target the server on a repo and build its map. |
where_is(query) |
Find where a symbol is defined, by name (substring, case-insensitive), ranked by contextual PageRank. |
grep_code(pattern) |
Regex search by content — each hit situated in its enclosing symbol (def/class/<module>), not a bare line. |
outline(file) |
Table of contents of a file: class/function signatures + line ranges. ~95 % fewer tokens than reading it. |
get_symbol(file, name) |
The full body of a single symbol — the only thing you actually read to start coding. |
who_references(name) |
Who calls a symbol (what a signature change might break). |
Languages
Python, JavaScript/JSX, TypeScript/TSX — via precompiled tree-sitter grammars (no C toolchain required, including on Windows).
Install
git clone https://github.com/noambinabout-boop/repo-map.git
cd repo-map
python -m venv .venv
# Windows: .venv\Scripts\activate
# Unix: source .venv/bin/activate
pip install -r requirements.txt # or: uv pip install -r requirements.txt
Wire it into Claude Code
Register the server (adjust the paths to your clone):
claude mcp add repo-map -- /path/to/repo-map/.venv/bin/python /path/to/repo-map/server.py
Then, from any session:
index("/path/to/the/project/you/want/to/explore")
where_is("MyClass")
outline("src/app.py")
get_symbol("src/app.py", "MyClass")
The server also runs standalone over stdio (python server.py) for any MCP-compatible client.
How it works
- Symbol graph. tree-sitter parses each file into definitions and a call/reference graph.
- Importance ranking. A PageRank variant weighted against popularity (
1/fan-in) so ubiquitous helpers don't drown out the code that actually structures the repo, merged with the import graph so shared components/constants aren't invisible. - Scope resolution.
self/cls/this, class inheritance (Python & JS/TSextends), named/namespace/default imports, and light type inference (x = Ctor(); x.foo()→Ctor.foo) are resolved to the right target. Every resolution is conservative: when a target is ambiguous, it falls back to a broad edge rather than dropping one — it never loses an edge, at worst it adds one. - Incremental cache. Parses are cached per file by mtime in
~/.repo-map/cache/(override withREPO_MAP_CACHE). Nothing is written into the repos you target. First index of a 284-file TS project: ~17 s; subsequent: ~0.3 s. - Per-repo ignores. Drop a
.repomapignore(.gitignoresyntax) at a repo root to keep generated/vendored dirs out of the graph.
Limitations (honest)
- PageRank is sharper on Python than on React/Expo. Structure there flows through JSX/imports/hooks, which the call graph doesn't see. The import-graph merge fixes "invisible shared components," but entry-point screens referenced only once by a route table can still rank low.
- Name-based resolution outside the cases above may add a spurious edge; it never drops one.
- Python
from . import x(no module name) is not resolved. - repo-map indexes structure, not literals — use
grep_codefor flags/config strings.
Tests
./.venv/Scripts/python.exe tests/run_tests.py
A non-regression suite of fixtures freezes each scope-resolution feature and compares the exact set of graph edges.
Prior art
The "repo map" idea was pioneered by Aider. repo-map is an independent MCP implementation with its own ranking, conservative scope resolution, and per-file incremental cache.
License
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。