GitHub GraphQL APIのクエリと使用のためのMCP（モデル制御プロトコル）ベースのツールです。このプロジェクトは、GitHub GraphQLスキーマを探索し、MCPクライアントツール（Claude AIなど）を介してGraphQLクエリを実行できるサーバーを提供します。
GitHub GraphQL API は、従来の REST API に比べて大きな利点を提供します。
正確なデータ取得:GraphQLを使用すると、クライアントは必要なフィールドを正確に指定でき、余分なデータを避けることができます。
トークン消費量の削減: 必要なフィールドのみを要求することで、API 応答サイズが大幅に削減され、AI モデルのトークン消費量が削減されます。
関連データに対する単一のリクエスト: 1回のクエリで複数の関連リソースを取得できるため、リクエスト数が削減されます。
自己文書化: 組み込みのドキュメントシステムを通じて、外部ドキュメントなしでAPIスキーマを直接照会して理解することができます。
強力な型システム: 型チェックを提供し、エラーを削減します
このプロジェクトは、これらの利点を活用して、GitHub GraphQL API スキーマを効果的に探索し、最適化されたクエリを実行するのに役立つツールを提供し、AI アシスタントに効率的な GitHub データ取得機能を提供します。
Related MCP server: @cloud9-labs/mcp-github
このツールは、次の一般的な操作を簡単に実装します。
リポジトリ基本情報クエリ: リポジトリ名、説明、スター数、ブランチリスト、その他の基本情報を取得します。
問題データの取得: 特定のリポジトリの問題リスト、詳細、またはコメントの内容を照会します。
ユーザープロフィールアクセス: ユーザーの個人プロフィール、貢献統計、その他の公開情報を取得します
プルリクエストステータスビュー: PRの基本ステータス、コメント内容、マージ情報を取得します
プロジェクト依存関係クエリ: プロジェクトの依存関係パッケージリストとバージョン情報を取得します
GraphQL の柔軟なクエリ機能を使用すると、次のような高度な分析機能を実装することもできます。
リポジトリ貢献傾向分析:コミットデータを集約し、プロジェクト活動を評価することで、コードの更新頻度と貢献者の参加を分析します。
問題管理と分類: カスタム条件に従って問題データを整理し、優先的に処理する必要がある問題を発見し、プロジェクト管理の効率を向上させます。
コードレビューパターン分析: PRコメントとレビュープロセスを分析し、一般的な問題パターンを特定し、コードレビューワークフローを最適化します。
貢献者ネットワークの可視化: プロジェクトの貢献者間の協力関係を構築し、主要な貢献者と専門分野を発見します。
依存関係の健全性評価: プロジェクトの依存関係の更新頻度と潜在的なセキュリティ問題を評価し、依存関係管理の提案を提供します。
GitHub GraphQL スキーマのルートタイプをクエリする (クエリ/ミューテーション)
特定のタイプの詳細なドキュメントを入手する
特定のフィールドのクエリドキュメントとパラメータ
GitHub GraphQL APIクエリを直接実行し、必要なデータを正確に取得してトークンの消費を削減します。
バイリンガルサポート（英語/中国語）
Python 3.10以上
GitHub 個人アクセス トークン (GitHub API にアクセスするためのもの)
Poetry（推奨依存関係管理ツール）
リポジトリをクローンします。
git clone https://github.com/wanzunz/github_graphql_api_mcp.git
cd github_graphql_api_mcpPoetry を使用して依存関係をインストールします。
# If you haven't installed Poetry yet, install it first:
# curl -sSL https://install.python-poetry.org | python3 -
# Install dependencies using Poetry
poetry install
# Activate the virtual environment
poetry shellPoetry を使用しない場合は、従来の方法を使用できます。
# Create and activate a virtual environment
python -m venv .venv
source .venv/bin/activate # Linux/MacOS
# or
.venv\Scripts\activate # Windows
# Install dependencies
pip install -e .環境変数を設定します。
.envファイルを作成し、GitHub 個人アクセス トークンを追加します。
GITHUB_TOKEN="your_github_token_here".env.exampleファイルをコピーして作成できます。
cp .env.example .env次に、 .envファイルを編集して、 your_github_token_here実際の GitHub トークンに置き換えます。
Poetry 仮想環境 ( poetry shell ) がアクティブになっていることを確認してから、次の手順を実行します。
python github_graphql_api_mcp_server.pyサーバーが起動したら、MCP クライアント (Claude AI など) を介してサーバーに接続できます。
Claude デスクトップ アプリでこの MCP サーバーを構成して、ワンクリックで起動することができます。
Claudeデスクトップアプリを開く
設定に移動し、MCPサーバー構成セクションを見つけます
次の構成を追加します (実際のパスに応じて変更してください)。
{
"mcpServers": {
"github_mcp": {
"command": "<your Python interpreter path>",
"args": [
"--directory",
"<project path>",
"run",
"github_graphql_api_mcp_server.py"
]
}
}
}設定例:
{
"mcpServers": {
"github_mcp": {
"command": "/usr/bin/python3",
"args": [
"--directory",
"/home/user/projects/github_graphql_api_mcp/",
"run",
"github_graphql_api_mcp_server.py"
]
}
}
}conda またはその他の環境管理ツールを使用する場合:
{
"mcpServers": {
"github_mcp": {
"command": "/opt/miniconda3/bin/python",
"args": [
"--directory",
"/Users/username/github/github_graphql_api_mcp/",
"run",
"github_graphql_api_mcp_server.py"
]
}
}
}設定後は、手動で起動しなくても、Claude デスクトップ アプリから直接 MCP サーバーを起動できます。
サーバーは次のツールを提供します。
print_type_field : GitHub GraphQL スキーマルートタイプのクエリフィールド
graphql_schema_root_type : ルートタイプ（クエリ/ミューテーション）のドキュメントを取得する
graphql_schema_type : 特定のタイプのクエリドキュメント
call_github_graphql : GitHub GraphQL APIクエリを実行する
MCP クライアントを使用してサーバーに接続した後、次の操作を実行できます。
クエリルートタイプのドキュメント:
Use the graphql_schema_root_type tool, parameter type_name="QUERY"特定のタイプのフィールドをクエリします。
Use the print_type_field tool, parameters type_name="QUERY", type_fields_name="repository"特定のタイプのクエリドキュメント:
Use the graphql_schema_type tool, parameter type_name="Repository"GraphQL クエリを実行します。
Use the call_github_graphql tool, parameter:
graphql="""
query {
viewer {
login
name
}
}
"""以下は、Claude と GitHub GraphQL API MCP を使用する例です。
使用する前に、GitHubトークンに適切な権限があることを確認してください。
トークンは.envファイルに保存されますが、バージョン管理システムにコミットしないでください。
クエリはGitHub APIの使用制限に準拠する必要があります
このプロジェクトは、MIT ライセンスに基づいてライセンスされています。これは、著作権表示とライセンス ステートメントを保持する限り、ユーザーがこのソフトウェアを自由に使用、変更、配布、および商用化できる、非常に寛容なライセンスです。
詳細な条件についてはMIT ライセンスを参照してください。
A tool to execute GitHub GraphQL API queries. Before using, it's recommended to check the documentation first, and include ID fields in your queries for easier follow-up operations Args: graphql: The GraphQL query Returns: str: Execution result
| Name | Required | Description | Default |
|---|---|---|---|
| graphql | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions checking documentation and including ID fields, which adds some operational context, but fails to address critical traits like authentication requirements, rate limits, error handling, or mutation vs. query behavior. For a GraphQL API tool with zero annotation coverage, this leaves significant gaps in understanding how the tool behaves in practice.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is appropriately sized and front-loaded, starting with the core purpose and usage recommendation in the first sentence. The Args and Returns sections are structured but could be more integrated. There's minimal waste, though the 'Returns: str: Execution result' is redundant given the output schema, slightly reducing efficiency.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (GraphQL API execution) and the presence of an output schema (which handles return values), the description is partially complete. It covers basic purpose and some usage tips but lacks details on authentication, error cases, or integration with sibling tools. Without annotations and with low schema coverage, it doesn't fully equip an agent for reliable tool invocation in a GitHub context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds minimal meaning beyond the input schema: it names the single parameter 'graphql' and states it's 'The GraphQL query', which the schema already indicates as a string type. With 0% schema description coverage, the description doesn't compensate by explaining query syntax, validation rules, or examples. The baseline is 3 because the schema covers the parameter's existence and type, but the description fails to enhance understanding significantly.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose as 'execute GitHub GraphQL API queries' with a specific verb (execute) and resource (GitHub GraphQL API queries). It distinguishes itself from sibling tools like graphql_schema_root_type and graphql_schema_type by focusing on query execution rather than schema exploration. However, it doesn't explicitly contrast with print_type_field, leaving some sibling differentiation incomplete.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides implied usage guidance by recommending checking documentation first and including ID fields for follow-up operations, which suggests context for when to use this tool effectively. However, it lacks explicit when/when-not criteria or named alternatives to sibling tools, leaving the agent to infer optimal usage scenarios without clear boundaries.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
A tool to query GitHub GraphQL schema root types. You need to provide the root type name (QUERY/MUTATION) Args: type_name: root type (QUERY or MUTATION) Returns: str: Documentation content
| Name | Required | Description | Default |
|---|---|---|---|
| type_name | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden but offers minimal behavioral context. It states the tool returns documentation content as a string but doesn't disclose authentication requirements, rate limits, error handling, or what specific documentation format to expect. The 'query' verb implies read-only, but this isn't explicitly confirmed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is appropriately sized with three sentences: purpose statement, parameter guidance, and return value. It's front-loaded with the core function. Minor improvements could include bullet points for Args/Returns, but overall it's efficient with minimal waste.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with no annotations, no output schema, and low schema coverage, the description is incomplete. It lacks details on authentication, error cases, the structure of returned documentation, or how this integrates with sibling tools. The return type 'str: Documentation content' is vague without examples or format specifications.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, but the description compensates by explaining that 'type_name' should be 'QUERY or MUTATION' and represents the 'root type name.' This adds meaningful context beyond the schema's generic 'Type Name' title, though it doesn't detail format constraints or examples.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose as 'query GitHub GraphQL schema root types' with specific resource (GitHub GraphQL schema) and verb (query). It distinguishes from sibling 'graphql_schema_type' by focusing on root types only, though it doesn't explicitly contrast with 'call_github_graphql' or 'print_type_field'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like 'graphql_schema_type' for non-root types or 'call_github_graphql' for actual queries. The description mentions needing to provide root type name but doesn't explain use cases or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
A tool to query specific type documentation in GitHub GraphQL schema. You need to provide the type_name
Args:
type_name: Type name like SecurityAdvisoryConnection
Returns:
str: Documentation content
| Name | Required | Description | Default |
|---|---|---|---|
| type_name | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool queries documentation, implying a read-only operation, but doesn't specify if it's safe, requires authentication, has rate limits, or what happens on errors. For a query tool with zero annotation coverage, this leaves significant behavioral gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is appropriately sized and front-loaded: the first sentence states the purpose clearly. The 'Args:' and 'Returns:' sections are structured but slightly redundant with the schema. It's concise with no wasted words, though the formatting could be more integrated.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's low complexity (1 parameter, no output schema, no annotations), the description is somewhat complete but has gaps. It covers the basic purpose and parameter semantics but lacks usage guidelines, behavioral details, and output explanation. For a simple query tool, it's adequate but not fully comprehensive.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 0%, so the description must compensate. It explains the single parameter 'type_name' as 'Type name like `SecurityAdvisoryConnection`,' adding meaning beyond the schema's basic 'string' type. This clarifies the parameter's purpose and provides an example, though it could be more detailed about valid type names or constraints.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'query specific type documentation in GitHub GraphQL schema.' It specifies the verb ('query'), resource ('type documentation'), and domain ('GitHub GraphQL schema'). However, it doesn't explicitly differentiate from sibling tools like 'graphql_schema_root_type' or 'print_type_field' beyond mentioning 'specific type' documentation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides minimal guidance: 'You need to provide the type_name' and gives an example ('SecurityAdvisoryConnection'). It doesn't explain when to use this tool versus alternatives like 'graphql_schema_root_type' or 'print_type_field,' nor does it mention prerequisites or exclusions. The guidance is basic and lacks context for tool selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
A tool to query GitHub GraphQL schema root type fields. You need to provide root_type_name and type_fields_name
Args:
type_name: root type like QUERY or MUTATION
type_fields_name: field name like repository based on root type documentation
Returns:
str: Documentation content for the specified field
| Name | Required | Description | Default |
|---|---|---|---|
| type_name | Yes | ||
| type_fields_name | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It discloses that the tool returns documentation content as a string, which is useful behavioral information. However, it doesn't mention whether this is a read-only operation, what happens with invalid inputs, if there are rate limits, authentication requirements, or error behavior. For a query tool with zero annotation coverage, this leaves significant behavioral gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is reasonably concise but has structural issues. The first sentence clearly states the purpose, but the parameter explanations are formatted as 'Args:' and 'Returns:' sections which are somewhat redundant with the schema. The information is front-loaded but could be more efficiently integrated. It's not excessively verbose but has minor organizational inefficiencies.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 2 parameters with 0% schema coverage and no output schema, the description provides adequate parameter semantics and specifies the return type as a string. However, it doesn't explain the format of the returned documentation content, error conditions, or authentication requirements. For a query tool with no annotations, this is minimally complete but lacks depth about operational behavior and integration context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate. It provides meaningful semantics for both parameters: 'type_name' is explained as 'root type like `QUERY` or `MUTATION`' and 'type_fields_name' as 'field name like `repository` based on root type documentation'. This adds substantial value beyond the bare schema, though it doesn't provide exhaustive examples or format details. With 2 parameters fully addressed, this exceeds the baseline expectation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'query GitHub GraphQL schema root type fields' with specific verbs ('query') and resources ('GitHub GraphQL schema root type fields'). It distinguishes from siblings like 'call_github_graphql' (which executes queries) and 'graphql_schema_type' (which might query non-root types), but doesn't explicitly contrast them. The purpose is specific but sibling differentiation is implied rather than explicit.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It mentions 'based on root type documentation' but doesn't specify when this tool is appropriate compared to sibling tools like 'graphql_schema_root_type' or 'graphql_schema_type'. There are no explicit when/when-not instructions or named alternatives, leaving usage context unclear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
call_github_graphqlgraphql_schema_root_typegraphql_schema_typeprint_type_fieldScored across 4 tools
The tools have overlapping purposes focused on GitHub GraphQL schema exploration, which could cause confusion. call_github_graphql is distinct for executing queries, but graphql_schema_root_type, graphql_schema_type, and print_type_field all retrieve schema documentation with subtle differences in scope (root types vs. specific types vs. root type fields). Descriptions help clarify, but an agent might struggle to choose between them for schema inspection tasks.
Tool names follow a consistent snake_case pattern with clear verb_noun structure (e.g., call_github_graphql, graphql_schema_type). Minor deviations exist, such as graphql_schema_root_type using 'root_type' while print_type_field uses 'type_field', but overall the naming is predictable and readable across all tools.
With 4 tools, the count is reasonable for a GitHub GraphQL API server, providing a focused set for query execution and schema exploration. It's slightly thin for comprehensive API coverage but well-scoped for its intended purpose, avoiding bloat while supporting core workflows like querying and schema lookup.
The tool set covers query execution and schema documentation retrieval, but has notable gaps for a GitHub API surface. It lacks CRUD operations for resources like repositories, issues, or pull requests, and doesn't support mutations or advanced query building. Agents can work around this by crafting GraphQL queries, but the surface is incomplete for typical GitHub automation tasks.
The Grafbase MCP server sits in front of a GraphQL API and exposes an MCP protocol-compliant interface that allows AI agents and LLMs to explore and query GraphQL APIs using natural language. It provides tools to search schemas, introspect types and fields, and execute GraphQL queries while minimizing context bloat by returning only relevant schema subsets, with built-in support for authentication, authorization, and configurable access control.
Repository knowledge graph MCP server for codebase understanding and debugging.
An MCP server that gives your AI access to the source code and docs of all public github repos
The Cortex MCP server provides read-only access to real-time engineering context from the Cortex developer portal, allowing AI coding assistants to answer natural language questions about your organization's catalog (microservices, libraries, domains, teams, infrastructure), scorecards (engineering standards and best practices), initiatives (goals and deadlines), and Engineering Intelligence metrics. It includes tools for querying documentation, tracking personal entities, and accessing AI-assisted insights across the entire Cortex ecosystem.
