# Woodpecker CI MCP for AI Agents AI Agent Connect > Woodpecker CI MCP lets you manage your CI/CD pipelines, monitor build agents, and configure repositories using natural language. It gives your AI agent direct access to your infrastructure so you can trigger builds, check health metrics, and manage secrets without leaving your chat window. ## Overview - **Category:** ship-it - **Price:** Free - **Endpoint:** https://edge.vinkius.com/vk_preview_FerYBzPY1px1PeVxdzIkY0bEgd6qWRE3xebiZbq6/ai-agent-connect - **Tags:** ci-cd, pipelines, automation, deployment, monitoring, build-management ## Description Woodpecker CI lets you manage your CI/CD instance through a chat interface. Instead of hunting through various dashboard tabs to find why a build failed, you can just ask your agent to check the status of a specific repository or restart a stalled pipeline. It handles the heavy lifting of repository management, like activating new projects or repairing broken webhooks, while keeping your secrets secure. When you use this on the Vinkius platform, you get a direct line to your infrastructure. You can manage global secrets, monitor the health of your build agents, and inspect pipeline configurations without ever leaving your current workspace. It turns your CI/CD management into a conversation rather than a series of manual clicks. You can quickly see which agents are online and which tasks they are currently processing. If a webhook stops reporting, you can fix it with a single command. This moves the complexity of CI/CD management into the background, letting you focus on shipping code instead of troubleshooting infrastructure. You can also audit permissions across your organization or pull metrics to see how your build capacity is being used. It is about making the maintenance of your CI/CD environment feel like a simple conversation. ## Tools ### get_pipeline_config Get the configuration files used for a pipeline. This is great for debugging build steps. ### list_org_secrets List organization-level secrets. Use this to manage shared credentials for a group of projects. ### list_orgs List all organizations. This helps you see the scope of your CI/CD environment. ### create_agent Create a new Woodpecker agent. This helps you scale your build capacity across different machines. ### delete_agent Delete an agent. Use this to clean up old runners or decommission hardware. ### get_org_permissions Get user permissions for an organization. Use this for auditing and access control. ### get_repo Get repository details. This helps you confirm the slug and status of a project. ### list_agents List all Woodpecker agents. This helps you monitor your total build capacity. ### cancel_pipeline Cancel a running pipeline. Use this to stop a build that is stuck or no longer needed. ### chown_repo Change repository owner to the current user. Use this to quickly reassign project permissions. ### create_global_secret Create a global secret. This is ideal for shared credentials like internal API keys. ### create_repo_secret Create a repository secret. Use this to store environment variables like database passwords. ### delete_pipeline Delete a pipeline. This helps keep your project history clean. ### delete_repo Deactivate or delete a repository. Use this when you no longer need a project's CI configuration. ### get_agent Get details of a specific agent. This helps you check its configuration and current status. ### get_healthz Server health check. Use this to see if your instance is responding correctly. ### get_metrics Prometheus metrics. This provides data on performance and resource usage for your infrastructure. ### get_pipeline Get details of a specific pipeline. Use this to see the status and ID of a recent build. ### get_user Get the currently authenticated user. Use this to confirm your identity within the system. ### get_version Get server version information. This is helpful for verifying you are on the latest release. ### list_agent_tasks List tasks currently assigned to an agent. Use this to troubleshoot why a build is pending. ### list_global_secrets List global secrets. Only use this if you have the necessary admin permissions. ### list_org_agents List agents scoped to an organization. This is useful for managing multi-tenant setups. ### list_pipelines List pipelines for a repository. Use this to track the history of your builds. ### list_repo_secrets List repository-level secrets. Use this to audit the credentials available to a project. ### list_repos List all repositories on the server. This helps you see every project you are tracking. ### list_users List all users. Only use this if you have admin rights for the system. ### lookup_repo Lookup a repository by its full name. Use this to quickly locate a project in a large organization. ### repair_repo Repair repository webhooks. Use this when a project stops triggering builds automatically. ### restart_pipeline Restart a pipeline. This is the quickest way to re-run a failed build. ### trigger_pipeline Trigger a manual pipeline. Use this to kick off a build on demand without a new commit. ### update_agent Update an existing agent. Use this to update runner settings or environment variables. ### update_repo Update repository settings. Use this to modify project names or visibility. ### activate_repo Activate a repository. Use this to make a new project available for CI/CD. ## Prompt Examples **Prompt:** ``` Are there any agents currently offline? ``` **Response:** ``` I've checked your agents. Here is the current status: | Agent Name | Status | Tasks | | :--- | :--- | :--- | | docker-runner-01 | **Online** | 2 | | k8s-runner-alpha | **Online** | 0 | | legacy-runner | **Offline** | 0 | Would you like me to check the tasks for the online agents? ``` **Prompt:** ``` Can you restart the last build for the auth-service repo? ``` **Response:** ``` I've located the latest pipeline for **auth-service** (#154). It failed at the 'integration-test' step. I have successfully restarted it for you. You can see the new build progress now. ``` **Prompt:** ``` List the secrets for the production project. ``` **Response:** ``` I've retrieved the secrets for the **production** repository: * `DB_PASSWORD`: ‮******** * `API_KEY`: ‮******** * `REDIS_URL`: ‮******** Let me know if you need to rotate any of these or create a new one. ``` ## Capabilities ### Trigger and restart builds Kick off manual pipelines or restart failed builds with a simple text command. ### Monitor agent health See which build runners are online and what tasks they are currently processing. ### Manage repository secrets Create and list secrets for specific projects to keep your credentials secure. ### Repair broken webhooks Fix repository connections that have stopped triggering builds automatically. ### Inspect build configurations View the configuration files and status of your existing pipelines to debug issues. ## Use Cases ### Restarting a failed build A developer sees a failed build in their terminal. They ask the agent to restart_pipeline for the auth-service repo, and it triggers the rerun immediately. ### Checking agent capacity An SRE notices slow build times. They ask the agent to list_agent_tasks to see which runners are overloaded and then use list_agents to find available capacity. ### Fixing webhook issues A project stops building on push. The admin asks the agent to repair_repo for the frontend project, which restores the connection without manual configuration. ### Managing shared secrets A security lead needs to update a shared database password. They ask the agent to create_global_secret to update the credentials for all projects at once. ## Benefits - Stop hunting through dashboard menus to find build statuses by using list_pipelines and get_pipeline. - Fix broken repository connections instantly with repair_repo to restore automatic builds. - Keep your infrastructure healthy by monitoring runner status with list_agents and get_healthz. - Manage sensitive credentials safely through create_repo_secret and list_repo_secrets. - Get immediate answers on your environment metrics with get_metrics and get_version. - Handle project onboarding faster by using activate_repo and chown_repo to set up new projects. ## How It Works The bottom line is you get a natural language interface for your entire CI/CD infrastructure. 1. Subscribe to the Woodpecker CI MCP on the Vinkius marketplace. 2. Provide your instance URL and a Personal Access Token in the configuration. 3. Ask your agent to manage your builds, check agent status, or update repository settings. ## Frequently Asked Questions **How do I use Woodpecker CI MCP to manage my builds?** You can use your AI agent to trigger builds, restart failed pipelines, and check the status of any repository. It replaces the need to manually click through the Woodpecker dashboard. **Can I use Woodpecker CI MCP to fix broken webhooks?** Yes. If your repository stops triggering builds automatically, you can ask the agent to repair the webhooks for that specific project. **Is Woodpecker CI MCP good for managing secrets?** It's a great way to manage credentials. You can create global or repository-specific secrets and list them using natural language commands. **How do I check my agent status with Woodpecker CI MCP?** You can simply ask your agent to list your runners or check their health. It will show you which ones are online and how many tasks they are currently running. **Can Woodpecker CI MCP trigger a build manually?** Yes, you can tell your agent to trigger a manual pipeline for any repository. This is perfect for testing changes without needing to commit new code. **Can I use Woodpecker CI MCP to see my pipeline history?** You can ask the agent to list the pipelines for a specific repository. It will show you the history of recent builds, including their success or failure status. **Can I trigger a new pipeline build for a specific repository?** Yes. Use the `trigger_pipeline` tool by providing the repository ID. You can also specify a branch or commit if needed to start a new execution immediately. **How do I check if my build agents are online and healthy?** You can use `list_agents` to see all connected agents and their status. For more detail on a specific agent, use `get_agent` or `list_agent_tasks` to see what it's currently working on. **Is it possible to manage environment secrets through this agent?** Yes, the server includes tools like `create_repo_secret` and `list_repo_secrets` to manage sensitive variables at the repository level, as well as global and organization-level secret tools.