Skip to main content
Glama
ko1ynnky

GitHub Actions MCP Server

by ko1ynnky

trigger_workflow

Trigger GitHub Actions workflows programmatically to automate CI/CD pipelines, run tests, or deploy code by specifying repository, workflow ID, branch, and input parameters.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
ownerYesRepository owner (username or organization)
repoYesRepository name
workflowIdYesThe ID of the workflow or filename (string or number)
refYesThe reference of the workflow run (branch, tag, or SHA)
inputsNoInput parameters for the workflow

Implementation Reference

  • The main handler function that implements the trigger_workflow tool. It validates inputs, constructs the GitHub API dispatch URL, sends a POST request with ref and optional inputs, and returns a success message.
    export async function triggerWorkflow(
      owner: string, 
      repo: string, 
      workflowId: string | number, 
      ref: string, 
      inputs?: Record<string, string>
    ) {
      owner = validateOwnerName(owner);
      repo = validateRepositoryName(repo);
    
      const url = `https://api.github.com/repos/${owner}/${repo}/actions/workflows/${workflowId}/dispatches`;
      
      const body: {
        ref: string;
        inputs?: Record<string, string>;
      } = { ref };
      
      if (inputs && Object.keys(inputs).length > 0) {
        body.inputs = inputs;
      }
    
      await githubRequest(url, {
        method: 'POST',
        body
      });
    
      // This endpoint doesn't return any data on success
      return { success: true, message: `Workflow ${workflowId} triggered on ${ref}` };
    }
  • Zod schema defining the input parameters for the trigger_workflow tool, used for validation.
    export const TriggerWorkflowSchema = z.object({
      owner: z.string().describe("Repository owner (username or organization)"),
      repo: z.string().describe("Repository name"),
      workflowId: z.string().describe("The ID of the workflow or filename (string or number)"),
      ref: z.string().describe("The reference of the workflow run (branch, tag, or SHA)"),
      inputs: z.record(z.string(), z.string()).optional().describe("Input parameters for the workflow"),
    });
  • src/index.ts:206-214 (registration)
    Registration of the trigger_workflow tool in the MCP server using server.tool(), providing the name, input schema, and handler that delegates to actions.triggerWorkflow.
    server.tool(
        "trigger_workflow",
        actions.TriggerWorkflowSchema.shape,
        async (request: any) => {
            const { owner, repo, workflowId, ref, inputs } = request;
            const result = await actions.triggerWorkflow(owner, repo, workflowId, ref, inputs);
            return { content: [{ type: "text", text: JSON.stringify(result) }] };
        }
    );
Behavior1/5

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

Tool has no description.

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

Conciseness1/5

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

Tool has no description.

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

Completeness1/5

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

Tool has no description.

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

Parameters1/5

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

Tool has no description.

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

Purpose1/5

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

Tool has no description.

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

Usage Guidelines1/5

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

Tool has no description.

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/ko1ynnky/github-actions-mcp-server'

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