Context7
Up-to-date docs for AI agents
作者による説明(英語の原文)
Local-first GitHub contribution research workbench
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": {
"gitcontribute": {
"command": "npx",
"args": [
"-y",
"gitcontribute"
]
}
}
}ターミナルでこれを実行します
claude mcp add gitcontribute -- npx -y gitcontributeプロジェクトの .cursor/mcp.json、または ~/.cursor/mcp.json に貼り付けます
{
"mcpServers": {
"gitcontribute": {
"command": "npx",
"args": [
"-y",
"gitcontribute"
]
}
}
}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": {
"gitcontribute": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"gitcontribute"
]
}
}
}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 morluto 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(3.0.2)がレジストリに届いたのは2 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Node.js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。
Contribution research for agents: check repository guidance, related work, code context, and validation before writing a patch.
Quick start · Workflow · CLI · MCP · Safety · Documentation
gitcontribute is available as a CLI, terminal UI, and MCP server for coding agents.
GitHub can show you open issues. It cannot tell you whether an issue is still relevant, already being implemented, appropriate for an outside contributor, or supported by enough evidence to work on safely.
GitContribute collects repository guidance, related issues and pull requests, code context, accepted contribution patterns, and validation results in a local SQLite corpus. Results identify missing or stale coverage.
find work -> understand it -> check competing work -> prove the change -> prepare the handoff
[!IMPORTANT]
GitContribute never writes to GitHub. It prepares local research and drafts
for you to review.
Run the guided setup with Node.js 18 or newer:
npx --yes gitcontribute@latest setup
Choose MCP to use GitContribute from a supported coding agent, CLI for the terminal and TUI, or Both. The wizard shows every planned change before applying it. Adding a repository during setup does not contact GitHub or start a sync.
After setup, start with a repository or an exact issue:
| Task | Coding agent | CLI |
|---|
| Find candidates | Find contribution candidates in owner/repo. Rank them by contribution fit, evidence, scope, and coordination risk. | gitcontribute archive sync owner/repo gitcontribute radar owner/repo --limit 10 | | Research an issue | Investigate owner/repo#42. Check guidance, discussion, code, prior fixes, competing work, and missing evidence. | gitcontribute archive sync owner/repo --numbers 42 gitcontribute research brief issue:owner/repo#42 |
Results include source references, coverage gaps, and suggested next steps.
Other installation options
Install a persistent command:
npm install --global gitcontribute@latest
gitcontribute setup
Pin GitContribute to a project:
npm install --save-dev gitcontribute
npm exec -- gitcontribute setup --mode mcp --codex --token-source none --yes
Build from source with Go 1.26 or newer:
go install github.com/morluto/gitcontribute/cmd/gitcontribute@latest
Native npm binaries are included for macOS ARM64/x64, Linux ARM64/x64, and Windows x64. You also need git. The gh CLI is optional and can provide authentication through gh auth token.
Search a repository or rank its open issues by available evidence, scope, risks, blockers, and signs that maintainer coordination is needed.
Find contribution candidates in golang/go. Exclude issues with active
implementation work and explain why each remaining candidate is worth investigating.
The ranking only covers stored observations. Results report incomplete coverage.
Build a research brief from the issue, repository guidance, discussion, linked work, indexed code, and historical contributions. Extracted maintainer text and checkboxes are not presented as complete acceptance criteria.
Investigate issue owner/repo#42. Summarize the confirmed problem, likely scope,
relevant code, maintainer guidance, and open questions.
Look for duplicate reports, linked pull requests, closing relationships, and semantically overlapping work before investing in an implementation.
Check whether owner/repo#42 has duplicate reports or competing implementation
work. Tell me what you checked and identify any missing coverage.
Incomplete coverage is reported instead of being treated as proof that no competing work exists. In the MCP workflow, follow the returned typed recovery action, poll the durable job, and reread the affected exact thread or repository before drawing that conclusion.
Record a reproduction, test, benchmark, or other validation and compare the unmodified baseline with a candidate. Validation commands run only after explicit approval.
Validate my candidate change against the baseline. Run the approved checks,
record both results, and explain whether the evidence supports the change.
Stored runs include the command, outcome, timing, and available process metrics.
Create a local issue, pull-request, or review draft tied to the research and validation evidence already collected.
Prepare a pull-request draft for this contribution. Tie its claims to the
recorded evidence, include the validation results, and do not post anything.
Draft revisions retain their exact rendered bytes and provenance.
GitContribute stores repositories, threads, code snapshots, investigations, evidence, validation results, and contribution outcomes in SQLite. Network access is explicit; once information has been synced, corpus search and inspection work offline.
GitHub read APIs Local checkout
| | | explicit sync / hydrate | explicit index / acquire v v +------------------------------------------------+ | Local SQLite corpus | | observations · coverage · evidence · outcomes | +------------------------+-----------------------+ | offline reads +---------+---------+ v v CLI / TUI Coding agents
The CLI and MCP server use the same application services and side-effect boundaries.
The CLI exposes the same workflow without requiring an MCP client:
# Sync repository context and current threads
gitcontribute archive sync-context owner/repo gitcontribute archive sync owner/repo
gitcontribute radar owner/repo --limit 10 gitcontribute research brief issue:owner/repo#42
gitcontribute search threads "connection timeout" --repo owner/repo gitcontribute search code "context.WithTimeout" --repo owner/repo
For implementation work:
gitcontribute investigation start-thread issue:owner/repo#42 --json
gitcontribute workspace create gitcontribute validation define --kind=test --command="go test ./..." \ --working-dir=/path/to/workspace gitcontribute validation run --kind=base --execute gitcontribute validation run --kind=candidate --execute gitcontribute validation compare gitcontribute readiness opportunity gitcontribute prepare pr --approach="Bound retries with context" \ --workspace
Run gitcontribute --help or gitcontribute --help for the complete command and flag reference. Most non-interactive commands accept --json; machine-readable output goes to stdout and progress goes to stderr.
Launch the local TUI with:
gitcontribute tui
The MCP server advertises one unified catalog. Hosts such as Codex and Claude Code can discover large MCP catalogs with native tool search, so setup does not ask users to choose permanent capability profiles.
gitcontribute setup --mode mcp --codex --token-source none --yes
gitcontribute setup --mode mcp --all-clients --token-source none --yes
To start the stdio server directly:
gitcontribute mcp serve --transport=stdio
Add --read-only to remove tools that permit network access, local writes, or execution. See MCP catalog and composition for capability boundaries, snapshot recovery, resource handoffs, and common tool sequences.
GitHub users are stored as first-class actors. Live discovery records identity only; profile, social-account, organization, pinned-item, repository, and contribution facts are synchronized independently. See the actor corpus for the data and freshness model.
GitContribute separates corpus reads, GitHub reads, local writes, process execution, and external mutation.
| Operation | Network | Local write | Runs a process | GitHub write |
|---|---|---|---|---|
| Search and inspect stored research | No | No | No | No |
| Record investigations and evidence | No | Yes | No | No |
| Sync or hydrate GitHub context | Yes | Yes | No | No |
| Acquire and index code | Yes | Yes | git only | No |
| Run an explicitly approved validation | No by default | Yes | Yes | No |
See Architecture for the complete boundary definitions.
GitContribute follows platform conventions:
| Platform | Configuration | Data |
|---|---|---|
| Linux | $XDG_CONFIG_HOME/gitcontribute or ~/.config/gitcontribute | $XDG_DATA_HOME/gitcontribute or ~/.local/share/gitcontribute |
| macOS | ~/Library/Application Support/gitcontribute | ~/Library/Application Support/gitcontribute/Data |
| Windows | %APPDATA%\gitcontribute | %LOCALAPPDATA%\gitcontribute\Data |
The default corpus is gitcontribute.db in the data directory. Run gitcontribute metadata or gitcontribute doctor --json to inspect the local setup.
Linux and macOS are the primary development and test targets. Windows builds are tested in CI and use the standard %APPDATA% and %LOCALAPPDATA% locations.
make verify
go run ./cmd/gitcontribute --help
Before changing package boundaries or side effects, read docs/architecture.md. See CONTRIBUTING.md for the repository workflow.