Context7
Up-to-date docs for AI agents
作者による説明(英語の原文)
Mines git history for file co-change patterns into a queryable knowledge graph via MCP.
この3つを1つのスコアにまとめることはしません。意見、測定、人気はそれぞれ別のものだからです。
このサーバーのやさしい解説はまだ書いていません。以下はレジストリから読み取った事実です。
使っているAIアプリを選んで、設定をコピーしてください。
必要なもの
どのアプリを使っていますか?
上でアプリを選んでください。選んだアプリを覚えておくので、次からはボタンに「…にインストール」と表示されます。
Claude Desktop → Settings → Developer → Edit Config を開き、claude_desktop_config.json にこれを貼り付けます
{
"mcpServers": {
"graphkeeper": {
"command": "uvx",
"args": [
"graphkeeper-cli",
"graphkeeper-mcp"
]
}
}
}ターミナルでこれを実行します
claude mcp add graphkeeper -- uvx graphkeeper-cli graphkeeper-mcpプロジェクトの .cursor/mcp.json、または ~/.cursor/mcp.json に貼り付けます
{
"mcpServers": {
"graphkeeper": {
"command": "uvx",
"args": [
"graphkeeper-cli",
"graphkeeper-mcp"
]
}
}
}ブラウザがアプリを開いてよいか確認し、そのあとアプリが設定を表示して確認を求めます。キーの値は空欄のままなので、自分で入力してください。
プロジェクトの .vscode/mcp.json に貼り付けます
{
"servers": {
"graphkeeper": {
"type": "stdio",
"command": "uvx",
"args": [
"graphkeeper-cli",
"graphkeeper-mcp"
]
}
}
}ブラウザがアプリを開いてよいか確認し、そのあとアプリが設定を表示して確認を求めます。キーの値は空欄のままなので、自分で入力してください。
これはパソコンで動くサーバーですが、ChatGPTがつなげるのはインターネット上のサーバーだけです。ほかのアプリを選んでください。
選んだアプリは、この端末のCookieに保存されます。アカウントは不要です。
この設定は、作者のレジストリ登録情報から作成しています。READMEと違う場合は、READMEに従ってください。
パソコンで動くサーバーです。インストールすると、ツール一覧がAIアプリに表示されます。
誰でも見られる情報をチェックしており、コードは読んでいません。当てはまらない項目は数に入れていません。 · 2026年11月6日にチェック
レジストリ名は、リポジトリを所有するGitHubアカウント RudrenduPaul で確認済みです
このリポジトリはまだGitHubから読み取っていません
このリポジトリはまだGitHubから読み取っていません
これはパソコンで動くため、インターネット上のエンドポイントはありません
パソコンで動き、代わりにローカルの設定を使います
パソコンで動くサーバーです。ツール一覧を読み取れるのは、インターネット上のエンドポイントがある場合だけです
レジストリでこのカテゴリにある有効なすべてのサーバーと比較しています。スターは、公開者がリポジトリの所有者である場合だけ数えます。
当てはまる基本チェック1項目のうち1項目に合格しました。コードは読んでいません。キーやトークンを追加する前に、サーバーがどんなアクセスを求めているかを確認し、必要な権限だけを持つキーを使ってください。
レジストリには必須のキーは載っていません。ただし、最初に使うときにサインインを求めるサーバーもあります。
あなたのパソコンで動きます。必要なときにAIアプリが起動し、データは作者のサーバーを通りません(サーバー自体がオンラインサービスを呼び出す場合を除きます)。
GitHubリポジトリの最終更新は–、最新バージョン(0.1.5)がレジストリに届いたのは3 か月前です。
Claude Desktop、Claude Code、Cursor、VS CodeなどのMCP対応アプリで使えます。パソコンにPython (uv)も必要です。
同じカテゴリには:Context7, Codebase Memory, Exa
同じカテゴリで、ほかの作者が作ったサーバー。スターの多い順。
カードの見方:★ GitHubスターi3つの柱:レビュー · チェック · 利用状況i更新=最新バージョンをレジストリに公開した日i
Up-to-date docs for AI agents
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
作者のリポジトリから書かれたとおりにコピーしたものです。PopNx MCPは内容を確認・推奨していません。HTML、画像、スクリプトは取り除いています。リンクはこのサイトの外へ移動します。
Install • Quickstart • CLI Reference • Comparison • FAQ
A local-only CLI that mines your git log for which files actually change together, then hands an AI coding agent a queryable answer instead of a grep across the whole history.
npx graphkeeper-cli build
npx graphkeeper-cli query co-change src/git.ts
Files that historically change alongside "src/git.ts":
1 src/store.ts 1 src/types.ts 1 test/git.test.ts 1 test/store.test.ts 1 test/test-helpers.ts
(Real output from running GraphKeeper against its own repo, this early in its history. Co-change counts grow as a codebase accumulates more commits.)
No server, no account, no embeddings API. Every byte of output comes from git log on the repo you already have checked out.
GraphKeeper ships two independent, equally first-class packages. Pick whichever fits your toolchain, or install both. Both mine the same git log co-change signal and share one on-disk .graphkeeper/graph.json schema, so a store built by either can be read back by the other.
# npm -- JavaScript/TypeScript CLI + library
npm install -g graphkeeper-cli
npx graphkeeper-cli build
pip install graphkeeper-cli
The npm package requires Node.js 18 or later; the Python package requires Python 3.9 or later. Both require git on your PATH. The Python package's CLI entry point is also graphkeeper (e.g. graphkeeper build). See python/README.md for the Python-specific walkthrough, and CHANGELOG.md for each distribution's version history.
Run it against any git repo, including this one:
git clone https://github.com/RudrenduPaul/GraphKeeper.git
cd GraphKeeper graphkeeper build
GraphKeeper build complete: /path/to/GraphKeeper
Co-change graph: 4 commit(s) analyzed, 80 file pair(s) found graphify enrichment: skipped -- graphify was not found on PATH. Install it with uv tool install graphifyy (or pipx install graphifyy) for symbol/call-graph enrichment; GraphKeeper works fine without it, in co-change-only mode.
Wrote /path/to/GraphKeeper/.graphkeeper/graph.json
Now query it:
graphkeeper query co-change src/git.ts
Files that historically change alongside "src/git.ts":
1 src/store.ts 1 src/types.ts 1 test/git.test.ts 1 test/store.test.ts 1 test/test-helpers.ts
If graphify is installed (uv tool install graphifyy), graphkeeper build automatically shells out to its local, no-API-key graphify extract --code-only and merges its symbol/call-graph into the same store, unlocking call-graph queries:
graphkeeper query calls mineCoChange
mineCoChange() (src/git.ts)
Calls (2): --> assertIsGitRepo() --> runGit()
Called by (1): <-- build()
(Also real output, from running graphkeeper build against this repo with graphify installed.)
Without graphify installed, that same command explains exactly why the answer isn't available instead of crashing or returning an empty result:
Call-graph query for "mineCoChange" is not available.
graphify was not found on PATH. Install it with uv tool install graphifyy (or pipx install graphifyy) for symbol/call-graph enrichment; GraphKeeper works fine without it, in co-change-only mode.
Every command also supports --json for scripts and agents:
graphkeeper query co-change src/git.ts --json
{
"file": "src/git.ts", "results": [ { "file": "src/store.ts", "count": 1 }, { "file": "src/types.ts", "count": 1 }, { "file": "test/git.test.ts", "count": 1 }, { "file": "test/store.test.ts", "count": 1 }, { "file": "test/test-helpers.ts", "count": 1 } ] }
graphkeeper build runs git log --no-merges --name-only across the full history of the repo and counts every file pair that changed together in the same commit. There's no guessing at coupling from folder structure or import statements alone; the answer comes from how the codebase actually got edited over time.PATH, graphkeeper build shells out to its local graphify extract --code-only --no-cluster and merges the resulting symbol/call edges into the same store, unlocking graphkeeper query calls. Without graphify, GraphKeeper still works in co-change-only mode and says so plainly instead of failing.graphkeeper query co-change --json and the equivalents return machine-readable output, so an agent's calling code parses a real data structure instead of scraping text.src/, TypeScript) and the PyPI package (python/src/graphkeeper/, Python) are independent ports, not a wrapper of one around the other. Both read and write the same .graphkeeper/graph.json, so a store built with one CLI is queryable from the other.spawnSync/subprocess.run with a list of arguments, so a crafted commit message or filename in the repo being analyzed can't be interpreted as shell syntax.Usage: graphkeeper [options] [command]
Options: -V, --version output the version number -h, --help display help for command
Commands: build [options] [path] Mine git history for co-change and (if available) merge in graphify's symbol/call graph query Query the GraphKeeper store built by graphkeeper build help [command] display help for command
graphkeeper build [path]Walks path (default: current directory), runs git log --no-merges --name-only across the whole history, and counts how often each pair of files was touched in the same commit. Writes the result to .graphkeeper/graph.json.
| Option | Description |
|---|---|
--json | emit machine-readable JSON instead of human-readable text |
--max-files-per-commit | skip commits touching more than this many files (default: 100), keeping a single mass-reformat or vendoring commit from drowning out real co-change signal |
--no-graphify | skip graphify enrichment even if graphify is installed |
If graphify is detected on PATH, build also runs graphify extract --code-only --no-cluster (graphify's own headless, local, no-API-key AST extraction path) into a directory inside .graphkeeper/, and merges its nodes/edges into the same store. The build output always states plainly whether that enrichment was included, and why it was skipped if not.
graphkeeper query co-change Lists files that historically changed alongside , ranked by how many commits touched both.
| Option | Description |
|---|---|
--json | emit machine-readable JSON instead of human-readable text |
--limit | cap the number of results |
--graph | path to a specific graph.json (default: /.graphkeeper/graph.json) |
Exit code 0 when results are found, 1 when there's no co-change data for that file yet, 2 on a usage or filesystem error.
graphkeeper query calls Shows callers and callees of , using graphify's calls edges from the most recent build. Only meaningful when that build included graphify enrichment; if it didn't, this prints a clear explanation of why instead of a crash or a silent empty result.
| Option | Description |
|---|---|
--json | emit machine-readable JSON instead of human-readable text |
--graph | path to a specific graph.json (default: /.graphkeeper/graph.json) |
Exit code 0 when the symbol is found, 1 when it isn't (or enrichment wasn't available), 2 on a usage or filesystem error.
GraphKeeper ships a Model Context Protocol server so an AI coding agent (Claude, Cursor, or any MCP-compatible client) can mine co-change history and query the graph directly, without a human invoking the CLI by hand.
Install the extra:
pip install "graphkeeper-cli[mcp]"
Add it to your MCP client's config (for Claude Desktop, claude_desktop_config.json):
{
"mcpServers": { "graphkeeper": { "command": "uvx", "args": ["--from", "graphkeeper-cli", "graphkeeper-mcp"] } } }
The server exposes one tool, run, that shells out to the published graphkeeper-cli npm package (via npx graphkeeper-cli) with the given subcommand and arguments plus --json, and returns the parsed JSON result:
run(["build", "."])
run(["query", "co-change", "src/git.ts"])
Transport is stdio, so there is nothing to host: the MCP client spawns the server as a local subprocess. Source: python/src/graphkeeper/mcp_server.py.
Both packages expose a real importable surface, listed below. The command line is a thin wrapper over the same functions.
graphkeeper-cli on npm)import { build, queryCoChange } from "graphkeeper-cli";
const result = build("."); console.log(${result.store.commitsAnalyzed} commit(s) analyzed);
const coChange = queryCoChange(result.store, "src/git.ts"); for (const row of coChange.results) { console.log(row.count, row.file); }
| Export | Signature | |
|---|---|---|
build | build(targetPath: string, options?: BuildOptions): BuildResult | |
queryCoChange | queryCoChange(store: GraphKeeperStore, file: string, options?: { limit?: number }): CoChangeQueryResult | |
queryCalls | queryCalls(store: GraphKeeperStore, symbol: string): CallsQueryResult | |
findGraphifyNode | `findGraphifyNode(nodes: GraphifyNode[], symbol: string): GraphifyNode \ | null` |
normalizeFileArg | normalizeFileArg(store: GraphKeeperStore, file: string): string |
| detectGraphify | `detectGr
冒頭だけを表示しています。続きはリポジトリで読めます