woodpecker-mcp
Read-only MCP server for Woodpecker CI that allows AI agents to check pipeline status and retrieve step logs across multiple self-hosted instances.
README
woodpecker-mcp
MCP (Model Context Protocol) server for Woodpecker CI. Gives AI agents and MCP clients read-only visibility into pipeline status and logs across multiple self-hosted Woodpecker instances — so a code reviewer (human or agent) can check whether CI is green and pull the failing step's output without leaving the conversation.
Built against the Woodpecker v3 REST API (verified on v3.16.0). No write operations: the server never restarts, approves, or cancels pipelines.
Tools
| Tool | Purpose |
|---|---|
list_instances |
List configured instances; check: true verifies connectivity + token per instance |
list_repos |
Repositories the token can access on an instance |
list_pipelines |
Recent pipelines for a repo, filterable by branch / event / status |
get_pipeline |
One pipeline with workflows, steps, exit codes, and failed_step_ids |
get_step_logs |
Log output of a step (tailed, default last 100 lines) |
Repos are addressed as owner/name or by numeric Woodpecker repo id. get_pipeline accepts number: "latest" (optionally with branch).
Configuration
Instances are configured via environment variables — one URL/token pair per instance:
# Single instance (named "default"). WOODPECKER_SERVER (the official CLI var) also works.
WOODPECKER_URL=https://ci.example.com
WOODPECKER_TOKEN=<personal access token>
# Or one pair per instance — the name becomes the `instance` argument on every tool:
WOODPECKER_PROD_URL=https://ci.example.com
WOODPECKER_PROD_TOKEN=...
WOODPECKER_STAGING_URL=https://ci.staging.example
WOODPECKER_STAGING_TOKEN=...
Tokens come from <server>/user/cli-and-api on each Woodpecker instance.
The server also loads a .env.woodpecker file from its working directory if present (MCP clients launch stdio servers with the project as working directory). Real environment variables take precedence over file values.
Instances with self-signed certificates: point Node at your CA with NODE_EXTRA_CA_CERTS=/path/to/ca.pem.
Usage with Claude Code
Register in a project's .mcp.json (or claude mcp add):
{
"mcpServers": {
"woodpecker": {
"command": "npx",
"args": ["-y", "github:RikiGomes/woodpecker-mcp"]
}
}
}
Alternatively, clone it once and point at the local build:
{
"mcpServers": {
"woodpecker": {
"command": "node",
"args": ["/path/to/woodpecker-mcp/dist/index.js"]
}
}
}
(after npm install && npm run build in the clone).
Development
Node >= 22.18 runs the TypeScript sources directly (type stripping):
npm install
npm run dev # run the server from src/
npm run check # typecheck
npm test # vitest
npm run build # emit dist/
Everything is plain ESM; relative imports use explicit .ts extensions and the build rewrites them to .js.
Testing with the MCP Inspector
The MCP Inspector is the quickest way to poke at the tools by hand:
npm run build
npx @modelcontextprotocol/inspector node dist/index.js -e WOODPECKER_URL=https://ci.example.com -e WOODPECKER_TOKEN=<token>
The Inspector does not pass your shell environment to the server it launches. Prefixing the command (WOODPECKER_URL=… npx @modelcontextprotocol/inspector …) or exporting beforehand sets the variable on the Inspector, not on this server — which then starts with no instances configured. Use one of:
- the
-e KEY=VALUEflags shown above — note they go afternode dist/index.js, not before; - the Environment Variables fields in the Inspector's connection pane (then Connect / Restart);
- a
.env.woodpeckerfile in the directory you launch from (the name is exact — a plain.envis not read).
Scripted checks work too, via the Inspector's CLI mode:
npx @modelcontextprotocol/inspector --cli node dist/index.js --method tools/list
npx @modelcontextprotocol/inspector --cli node dist/index.js --method tools/call --tool-name list_instances
Design notes
- Read-only by contract. Intended for reviewer agents; there is deliberately no restart/approve/cancel surface.
- Log tailing. Woodpecker returns a step's entire stored log in one response;
get_step_logstails (default 100 lines, max 2000) to protect the caller's context window. Exit-code entries are labelled[exit code]. - Slug resolution.
owner/nameis resolved via/api/repos/lookup/…once and cached per process. - Sub-path hosting. Instance base URLs may include a sub-path (
WOODPECKER_ROOT_PATHinstalls).
License
MIT — see 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。