用于 GitHub Actions 集成的模型上下文协议服务器。
这是一个基于 TypeScript 的 MCP 服务器，专为 GitHub Actions 集成而设计。它提供以下功能：
从存储库获取可用 GitHub Actions 的工具
获取特定 GitHub Action 详细信息的工具
触发 GitHub 工作流调度事件的工具
从 GitHub 存储库获取最新版本的工具
Related MCP server: GitHub MCP Server
get_github_actions - 获取存储库可用的 GitHub Actions
必需参数： owner （仓库所有者，用户名或组织）和repo （仓库名称）
可选参数： token （GitHub个人访问令牌，用于访问私有仓库或增加API速率限制）
返回包含工作流 ID、名称、路径、状态、URL 和内容的 JSON 数据
get_github_action - 获取有关特定 GitHub Action 的详细信息，包括输入及其要求
必需参数： owner （操作所有者，用户名或组织）和repo （操作的存储库名称）
可选参数：
path ：动作定义文件的路径（默认值：'action.yml'）
ref ：Git 引用（分支、标签或提交 SHA，默认值：'main'）
token ：GitHub 个人访问令牌（可选）
返回有关操作的详细信息，包括名称、描述、作者、输入（以及是否需要）等。
trigger_github_action - 触发 GitHub 工作流并传递相关参数
必需参数：
owner ：存储库所有者（用户名或组织）
repo ：存储库名称
workflow_id ：要触发的工作流的 ID 或文件名
可选参数：
ref ：触发工作流程的 git 引用（默认值：'main'）
inputs ：传递给工作流的输入（必须与工作流定义的输入匹配）
token ：GitHub 个人访问令牌（必须具有工作流范围）
返回工作流运行信息，包括状态、URL 等。
get_github_release - 从 GitHub 存储库获取最新的 2 个版本
必需参数： owner （仓库所有者，用户名或组织）和repo （仓库名称）
可选参数： token （GitHub个人访问令牌，可选）
返回有关最新 2 个版本的信息
最简单的安装和使用方法是通过 Claude Desktop 配置文件中的npx命令，无需手动本地安装：
{
"mcpServers": {
"github-action-trigger-mcp": {
"command": "npx",
"args": [
"-y",
"@nextdrive/github-action-trigger-mcp"
],
"env": {
"GITHUB_PERSONAL_ACCESS_TOKEN": "your_github_token_here"
}
}
}
}此方法的好处：
无需安装本地包
自动使用最新版本
一次设置即可使用
内置 GitHub 令牌配置
如果您希望手动安装，请按照以下步骤操作：
安装软件包：
npm install -g @nextdrive/github-action-trigger-mcp在 Claude Desktop 配置中使用：
在 MacOS 上： ~/Library/Application Support/Claude/claude_desktop_config.json在 Windows 上： %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"github-action-trigger-mcp": {
"command": "@nextdrive/github-action-trigger-mcp",
"env": {
"GITHUB_PERSONAL_ACCESS_TOKEN": "your_github_token_here"
}
}
}
}要访问 GitHub API（尤其是私有仓库或工作流触发器），您需要配置 GitHub 个人访问令牌。有几种方法可以做到这一点：
通过env字段直接在 Claude Desktop 配置文件中设置令牌：
"env": {
"GITHUB_PERSONAL_ACCESS_TOKEN": "your_github_token_here"
}设置GITHUB_TOKEN环境变量：
# On Linux/MacOS
export GITHUB_TOKEN=your_github_token
# On Windows
set GITHUB_TOKEN=your_github_token编辑配置文件：
~/.nextdrive-github-action-trigger-mcp/config.json设置你的 GitHub 令牌：
{
"githubToken": "your_github_token"
}服务器第一次启动时会自动创建此配置文件的模板。
安装依赖项：
npm install构建服务器：
npm run build对于开发过程中的自动重建：
npm run watch使用 MCP Inspector 进行调试：
npm run inspector检查器将提供一个 URL 来访问浏览器中的调试工具。
如果要将此包发布到 npm，请按照以下步骤操作：
确保您已登录 npm 并具有发布到@nextdrive组织的权限：
npm login构建项目：
npm run build发布到 npm（组织范围的包默认是私有的，使用--access public将其公开）：
npm publish --access public发布后，任何人都可以使用npx @nextdrive/github-action-trigger-mcp命令运行此工具或在其 Claude Desktop 配置中使用它。
使用get_github_actions工具获取存储库的 GitHub Actions：
{
"owner": "username-or-org",
"repo": "repository-name"
}如果配置了默认令牌，则访问私有存储库时将自动使用它。
响应示例：
[
{
"id": 12345678,
"name": "CI",
"path": ".github/workflows/ci.yml",
"state": "active",
"url": "https://github.com/owner/repo/actions/workflows/ci.yml",
"content": "name: CI\n\non:\n push:\n branches: [ main ]\n pull_request:\n branches: [ main ]\n\njobs:\n build:\n runs-on: ubuntu-latest\n steps:\n - uses: actions/checkout@v2\n - name: Setup Node.js\n uses: actions/setup-node@v2\n with:\n node-version: 16.x\n - name: Install dependencies\n run: npm ci\n - name: Build\n run: npm run build\n - name: Test\n run: npm test\n"
}
]使用get_github_action工具获取特定 Action 的详细信息：
{
"owner": "actions",
"repo": "checkout",
"ref": "v4"
}响应示例：
{
"name": "Checkout",
"description": "Check out a Git repository at a particular version",
"author": "GitHub",
"inputs": [
{
"name": "repository",
"description": "Repository name with owner. For example, actions/checkout",
"default": "",
"required": false
},
{
"name": "ref",
"description": "The branch, tag or SHA to checkout.",
"default": "",
"required": false
}
],
"runs": {
"using": "node20",
"main": "dist/index.js"
}
}使用trigger_github_action工具触发GitHub工作流程：
{
"owner": "username-or-org",
"repo": "repository-name",
"workflow_id": "ci.yml",
"inputs": {
"deploy_environment": "production",
"debug_enabled": "true"
}
}响应示例：
{
"success": true,
"message": "Workflow dispatch event triggered successfully",
"run": {
"id": 12345678,
"url": "https://github.com/owner/repo/actions/runs/12345678",
"status": "queued",
"conclusion": null,
"created_at": "2025-03-19T06:45:12Z",
"triggered_by": "API"
}
}注意：触发工作流需要：
必须配置工作流以支持workflow_dispatch事件
GitHub 令牌必须具有workflow范围权限
传递的输入参数必须与工作流中定义的参数匹配
使用get_github_release工具从存储库获取最新的 2 个版本：
{
"owner": "username-or-org",
"repo": "repository-name"
}响应示例：
{
"count": 2,
"releases": [
{
"id": 12345678,
"name": "v1.0.0",
"tag_name": "v1.0.0",
"published_at": "2025-03-15T10:00:00Z",
"draft": false,
"prerelease": false,
"html_url": "https://github.com/owner/repo/releases/tag/v1.0.0",
"body": "Release notes for version 1.0.0",
"assets": [
{
"name": "app-v1.0.0.zip",
"size": 1234567,
"download_count": 42,
"browser_download_url": "https://github.com/owner/repo/releases/download/v1.0.0/app-v1.0.0.zip",
"created_at": "2025-03-15T10:05:00Z",
"updated_at": "2025-03-15T10:05:00Z"
}
],
"author": {
"login": "username",
"html_url": "https://github.com/username"
}
},
{
"id": 87654321,
"name": "v0.9.0",
"tag_name": "v0.9.0",
"published_at": "2025-03-01T10:00:00Z",
"draft": false,
"prerelease": true,
"html_url": "https://github.com/owner/repo/releases/tag/v0.9.0",
"body": "Pre-release notes for version 0.9.0",
"assets": [],
"author": {
"login": "username",
"html_url": "https://github.com/username"
}
}
]
}Enable auto-merge for a specific pull request. This will automatically merge the PR when all required checks pass.
| Name | Required | Description | Default |
|---|---|---|---|
| owner | Yes | Owner of the repository (username or organization) | |
| repo | Yes | Name of the repository | |
| pull_number | Yes | The pull request number | |
| merge_method | No | The merge method to use when auto-merging (MERGE, SQUASH, or REBASE) | |
| token | No | GitHub personal access token (optional) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. While it states the tool enables auto-merge and describes the triggering condition, it lacks critical information about permissions needed, whether this is reversible, rate limits, error conditions, or what happens to existing auto-merge settings. For a mutation tool with zero annotation coverage, this is insufficient.
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 perfectly concise with two sentences that directly communicate the core functionality. Every word earns its place, and it's front-loaded with the main purpose.
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 mutation tool with no annotations and no output schema, the description is incomplete. It doesn't address permissions, error handling, return values, or important behavioral details like whether this overrides existing settings or requires specific repository configurations. The context signals show this is a non-trivial operation (5 parameters, 3 required), warranting more comprehensive documentation.
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 100%, so the schema fully documents all 5 parameters. The description doesn't add any parameter-specific information beyond what's in the schema, but it does provide context about the overall purpose that helps understand parameter usage. Baseline 3 is appropriate when schema does the heavy lifting.
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 specific action ('Enable auto-merge') and the target resource ('for a specific pull request'), with additional detail about the automatic merging behavior when checks pass. It distinguishes itself from sibling tools (which are all read operations) by being a write/mutation tool.
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, prerequisites, or constraints. It mentions the condition 'when all required checks pass' but doesn't specify what happens if checks fail or if there are other requirements like permissions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get detailed information about a specific GitHub Action, including inputs and their requirements
| Name | Required | Description | Default |
|---|---|---|---|
| owner | Yes | Owner of the action (username or organization) | |
| repo | Yes | Repository name of the action | |
| path | No | Path to the action.yml or action.yaml file (usually just 'action.yml') | |
| ref | No | Git reference (branch, tag, or commit SHA, default: main) | |
| token | No | GitHub personal access token (optional) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden for behavioral disclosure. It describes what information is returned but lacks details on permissions required (e.g., public vs. private repos), rate limits, error conditions, or response format. For a tool with no annotations, 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 a single, efficient sentence that directly states the tool's purpose without unnecessary words. It's front-loaded with the core functionality and includes a useful detail about inputs and requirements. Every part of the sentence earns its place.
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 no annotations and no output schema, the description is minimally adequate for a read-only tool. It clarifies the scope (detailed info about a specific action) but doesn't address behavioral aspects like authentication needs or response structure. For a tool with 5 parameters and no structured safety hints, it should provide more context about usage constraints.
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 100%, so the schema already documents all 5 parameters thoroughly. The description adds no parameter-specific information beyond what's in the schema (e.g., it doesn't clarify 'path' defaults or 'token' usage scenarios). Baseline 3 is appropriate when schema does the heavy lifting.
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: 'Get detailed information about a specific GitHub Action, including inputs and their requirements.' It specifies the verb ('Get') and resource ('GitHub Action') with additional detail about what information is retrieved. However, it doesn't explicitly differentiate from sibling tools like 'get_github_actions' (plural vs. singular).
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 doesn't mention sibling tools like 'get_github_actions' (which likely lists multiple actions) or 'trigger_github_action' (which executes an action). There's no context about prerequisites, limitations, or typical use cases.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get available GitHub Actions for a repository
| Name | Required | Description | Default |
|---|---|---|---|
| owner | Yes | Owner of the repository (username or organization) | |
| repo | Yes | Name of the repository | |
| token | No | GitHub personal access token (optional) |
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 insight. It doesn't disclose whether this is a read-only operation, what authentication is required (though 'token' is optional in schema), rate limits, pagination, or what 'available' means (e.g., active vs. all actions). This leaves significant gaps for safe invocation.
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 a single, clear sentence with zero wasted words. It's front-loaded with the core purpose and appropriately sized for a straightforward tool, making it easy to parse quickly.
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 and no output schema, the description is insufficient. It doesn't explain what 'available GitHub Actions' entails (e.g., list format, metadata included), authentication needs despite an optional token, or error handling. Given the complexity of GitHub APIs and sibling tools, more context is needed for reliable use.
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 100%, so parameters are well-documented in the schema itself. The description adds no additional meaning beyond implying the tool fetches actions for a repository, which aligns with the schema but doesn't enhance parameter understanding. Baseline 3 is appropriate given high schema coverage.
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 action ('Get') and resource ('GitHub Actions for a repository'), making the purpose immediately understandable. However, it doesn't differentiate from sibling tools like 'get_github_action' (singular) or 'get_github_release', leaving some ambiguity about scope.
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. The description doesn't mention prerequisites, constraints, or relationships with sibling tools like 'get_github_action' (singular) or 'trigger_github_action', leaving the agent to infer usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get the latest 2 releases from a GitHub repository
| Name | Required | Description | Default |
|---|---|---|---|
| owner | Yes | Owner of the repository (username or organization) | |
| repo | Yes | Name of the repository | |
| token | No | GitHub personal access token (optional) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states what the tool does but lacks critical details like whether it requires authentication (though the token parameter is optional in the schema), rate limits, error handling, or the format of returned data. This leaves significant gaps in understanding the tool's behavior.
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 a single, direct sentence that efficiently conveys the core functionality without unnecessary words. It is front-loaded and appropriately sized for the tool's scope, making it easy to understand at a glance.
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 complexity of interacting with GitHub APIs, no annotations, and no output schema, the description is incomplete. It fails to address key aspects like authentication needs, rate limiting, error responses, or the structure of the release data returned, which are essential for effective tool usage in a real-world 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 input schema has 100% description coverage, clearly documenting all parameters (owner, repo, token). The description does not add any additional meaning or context beyond what the schema provides, such as explaining the 'latest 2 releases' constraint or token usage. Baseline 3 is appropriate as the schema handles parameter documentation adequately.
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 action ('Get') and resource ('latest 2 releases from a GitHub repository'), making the purpose specific and understandable. However, it doesn't explicitly differentiate from sibling tools like 'get_github_action' or 'get_github_actions', which focus on GitHub Actions rather than releases, so it misses full sibling distinction.
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, such as when to choose it over other GitHub-related tools or how it fits into broader workflows. There is no mention of prerequisites, exclusions, or contextual usage scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Trigger a GitHub workflow dispatch event with custom inputs
| Name | Required | Description | Default |
|---|---|---|---|
| owner | Yes | Owner of the repository (username or organization) | |
| repo | Yes | Name of the repository | |
| workflow_id | Yes | The ID or filename of the workflow to trigger | |
| ref | No | The git reference to trigger the workflow on (default: main) | |
| inputs | No | Inputs to pass to the workflow (must match the workflow's defined inputs) | |
| token | No | GitHub personal access token (must have workflow scope) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions 'trigger' and 'custom inputs,' which implies a write operation, but lacks details on permissions required (beyond the token parameter), rate limits, whether the action is idempotent, what happens on failure, or the expected response format. This leaves significant gaps for an agent to understand the tool's behavior.
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 a single, efficient sentence that front-loads the core purpose ('Trigger a GitHub workflow dispatch event') and adds necessary context ('with custom inputs'). There is no wasted verbiage, and it directly communicates the tool's function without redundancy.
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 complexity of triggering GitHub actions (a write operation with multiple parameters and no output schema), the description is insufficient. It lacks details on behavioral aspects like authentication needs, error handling, or response structure, which are critical for an agent to use the tool effectively. The high schema coverage helps with parameters, but overall completeness is poor due to missing operational 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 input schema has 100% description coverage, so the schema already documents all six parameters thoroughly. The description adds minimal value beyond implying that 'custom inputs' map to the 'inputs' parameter, but it doesn't provide additional syntax, format details, or constraints not covered in the schema. This meets the baseline for high schema coverage.
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 specific action ('trigger') and resource ('GitHub workflow dispatch event') with additional context ('with custom inputs'). It distinguishes from sibling tools like 'get_github_action' or 'enable_pull_request_automerge' by focusing on initiating workflows rather than retrieving information or modifying settings.
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 explicit guidance is provided on when to use this tool versus alternatives. While it's implied for triggering workflows, there's no mention of prerequisites (e.g., needing a GitHub token with specific scopes), when not to use it (e.g., for manual triggers vs. automated ones), or how it differs from other workflow-related tools in the ecosystem.
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.
v1.0.0enable_pull_request_automergeget_github_actionget_github_actionsget_github_releasetrigger_github_actionScored across 5 tools
Most tools have distinct purposes: enabling auto-merge, getting action details, listing available actions, fetching releases, and triggering actions. However, 'get_github_action' and 'get_github_actions' could be slightly confusing as they both retrieve action information but differ in scope (single vs. multiple). The descriptions clarify this, but the names are similar enough to cause potential misselection.
The naming follows a consistent verb_noun pattern with 'get', 'enable', and 'trigger' as verbs, all using snake_case. The only minor deviation is 'enable_pull_request_automerge' which includes a compound noun, but it still fits the overall style. This consistency makes the tools predictable and easy to understand.
With 5 tools, the count is well-scoped for a GitHub Action Trigger server, covering key operations like triggering actions, managing auto-merge, and retrieving related information. It's slightly lean but reasonable, as it focuses on core functionality without unnecessary bloat, though a few more tools might enhance coverage.
The toolset covers triggering actions and getting action/release info, but has notable gaps. For example, there's no way to disable auto-merge, manage action runs (e.g., cancel or list workflows), or handle other GitHub Actions lifecycle aspects like secrets or environments. This limits agents to basic triggering and info retrieval, with missing operations that could cause workarounds or failures.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Model Context Protocol server for the Apideck Unified API. Connect any MCP-compatible agent framework to 100+ accounting systems, HRIS platforms, file storage providers, and more through one integration. More information https://www.apideck.com/mcp-server
A Model Context Protocol server for Wix AI tools
The Mercado Pago MCP Server implements the Model Context Protocol to provide AI agents and LLMs with access to Mercado Pago's APIs and tools within compatible development environments. It acts as an intermediary that translates Mercado Pago resources into executable functions (tools) that AI applications can invoke to perform actions and automate flows. The server simplifies integration, enables using documentation to implement or improve code, and optimizes operations through natural language interactions without manual implementations.
