Agentled MCP Server

Instructions

Implementation Reference

• src/tools/executions.ts:54-73 (handler)

  Registration and handler implementation for the 'get_execution' MCP tool.

      server.tool(
          'get_execution',
          `Get full execution details including results from each completed step.
  The executionContent field maps stepId -> step output data.
  Use this to inspect what a workflow produced, debug failures, or check intermediate results.`,
          {
              workflowId: z.string().describe('The workflow ID'),
              executionId: z.string().describe('The execution ID'),
          },
          async ({ workflowId, executionId }, extra) => {
              const client = clientFactory(extra);
              const result = await client.getExecution(workflowId, executionId);
              return {
                  content: [{
                      type: 'text' as const,
                      text: JSON.stringify(result, null, 2),
                  }],
              };
          }
      );