Skip to main content
Glama

trigger_pipeline

Trigger a new CI/CD pipeline on a GitLab project for a given branch or tag, using an optional authentication token.

Instructions

Trigger a new pipeline.

Args:
    project_id: GitLab project ID
    ref: Branch/tag to run pipeline on (default: main)
    token: GitLab Personal Access Token (optional)
    ctx: MCP context (automatically injected)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
project_idYes
refNomain
tokenNo
ctxNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Implementation Reference

  • The async function that implements the trigger_pipeline tool logic. It takes project_id, ref (default 'main'), token, and ctx, then POSTs to the GitLab API endpoint /projects/{project_id}/pipeline with the ref data and returns the pipeline ID.
    @mcp.tool()
    async def trigger_pipeline(project_id: int, ref: str = "main", token: str = None, ctx=None) -> str:
        """Trigger a new pipeline.
        
        Args:
            project_id: GitLab project ID
            ref: Branch/tag to run pipeline on (default: main)
            token: GitLab Personal Access Token (optional)
            ctx: MCP context (automatically injected)
        """
        endpoint = f"/projects/{project_id}/pipeline"
        data = {"ref": ref}
        result = await make_gitlab_request(endpoint, "POST", data, ctx=ctx, token=token)
        
        if isinstance(result, dict) and "error" in result:
            return f"Error triggering pipeline: {result['error']}"
        
        return f"Pipeline triggered successfully: #{result['id']} on {ref}"
  • The @mcp.tool() decorator on line 536 registers the trigger_pipeline function as an MCP tool with the FastMCP server instance.
    @mcp.tool()
    async def trigger_pipeline(project_id: int, ref: str = "main", token: str = None, ctx=None) -> str:
  • The function signature defines the input schema: project_id (int, required), ref (str, default 'main'), token (optional str), ctx (auto-injected context). The return type is str.
    async def trigger_pipeline(project_id: int, ref: str = "main", token: str = None, ctx=None) -> str:
        """Trigger a new pipeline.
        
        Args:
            project_id: GitLab project ID
            ref: Branch/tag to run pipeline on (default: main)
            token: GitLab Personal Access Token (optional)
            ctx: MCP context (automatically injected)
        """
        endpoint = f"/projects/{project_id}/pipeline"
        data = {"ref": ref}
        result = await make_gitlab_request(endpoint, "POST", data, ctx=ctx, token=token)
  • The helper function that trigger_pipeline calls to make the actual HTTP POST request to the GitLab API. It handles token resolution, header construction, and HTTP request execution.
    async def make_gitlab_request(endpoint: str, method: str = "GET", data: dict = None, ctx=None, token: str = None) -> dict[str, Any] | None:
        """Make a request to GitLab API with proper error handling."""
        # Priority: 1. Explicit token parameter, 2. Context headers, 3. Environment variable
        
        # If no explicit token provided, try to get from context
        if not token and ctx and hasattr(ctx, 'request_context') and ctx.request_context:
            # Try to get from request headers
            if hasattr(ctx.request_context, 'headers'):
                token = ctx.request_context.headers.get('GITLAB_TOKEN')
        
        # Fallback to environment variable
        if not token:
            token = os.getenv("GITLAB_TOKEN")
        
        if not token:
            return {"error": "GitLab token not provided. Please provide a token parameter, GITLAB_TOKEN in the request headers, or set the environment variable."}
        
        # Get GitLab URL (from context or environment)
        gitlab_url = os.getenv("GITLAB_URL", "https://gitlab.com")
        
        headers = {
            "PRIVATE-TOKEN": token,
            "Content-Type": "application/json"
        }
        
        url = f"{gitlab_url}/api/v4{endpoint}"
        
        async with httpx.AsyncClient() as client:
            try:
                if method == "GET":
                    response = await client.get(url, headers=headers, timeout=30.0)
                elif method == "POST":
                    response = await client.post(url, headers=headers, json=data, timeout=30.0)
                elif method == "PUT":
                    response = await client.put(url, headers=headers, json=data, timeout=30.0)
                elif method == "DELETE":
                    response = await client.delete(url, headers=headers, timeout=30.0)
                
                response.raise_for_status()
                return response.json() if response.content else {"success": True}
            except Exception as e:
                return {"error": str(e)}
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, and the description fails to disclose behavioral traits such as whether the pipeline execution is destructive, required permissions (token optional but unclear if always needed), or rate limits. The word 'Trigger' implies action but lacks detail.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise with no wasted words. It starts with the primary action and then lists parameters in a clear, structured format. Every sentence is meaningful.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given that an output schema exists (though not shown) and the description covers all parameters, it is largely complete. However, missing usage guidelines and behavioral disclosures slightly reduce completeness for an agent deciding whether to invoke this tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description adds essential meaning by explaining each parameter: project_id, ref (with default), token (optional), and ctx (auto-injected). This goes beyond the bare schema, though ctx could be described more clearly.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Trigger a new pipeline', which is a specific verb+resource combination. It distinguishes from sibling tools like get_pipelines which are read-only, so an agent can easily differentiate.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description does not provide any guidance on when to use this tool versus alternatives (e.g., get_pipelines for listing). It only lists arguments, leaving the agent without context on appropriate usage scenarios.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/skmprb/gitlab-clone-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server