Skip to main content
Glama

create_workflow

Build and configure automated workflows by defining pipeline steps, triggers, and actions within the Agentled MCP Server platform.

Instructions

Create a new workflow from a pipeline definition. The pipeline object should include:

  • name (required): Workflow name

  • goal: What the workflow does

  • description: Longer description

  • steps: Array of pipeline steps (trigger, aiAction, appAction, milestone, etc.)

  • context: Execution input config and input/output pages

  • metadata: Template info, notifications, ROI

  • style: UI styling (colors, icon)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pipelineYesThe pipeline definition object
localeNoLocale (default: en)

Implementation Reference

  • Tool registration for create_workflow in src/tools/workflows.ts.
        server.tool(
            'create_workflow',
            `Create a new workflow from a pipeline definition. The pipeline object should include:
    - name (required): Workflow name
    - goal: What the workflow does
    - description: Longer description
    - steps: Array of pipeline steps (trigger, aiAction, appAction, milestone, etc.)
    - context: Execution input config and input/output pages
    - metadata: Template info, notifications, ROI
    - style: UI styling (colors, icon)`,
            {
                pipeline: z.record(z.string(), z.any()).describe('The pipeline definition object'),
                locale: z.string().optional().describe('Locale (default: en)'),
            },
            async ({ pipeline, locale }, extra) => {
                const client = clientFactory(extra);
                const result = await client.createWorkflow(pipeline, locale);
                return {
                    content: [{
                        type: 'text' as const,
                        text: JSON.stringify(result, null, 2),
                    }],
                };
            }
        );
  • The handler implementation for create_workflow, which wraps an API request to /api/external/workflows.
    async createWorkflow(pipeline: Record<string, any>, locale?: string) {
        return this.request('/workflows', {
            method: 'POST',
            body: JSON.stringify({ pipeline, locale }),
        });
    }

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/Agentled/mcp-server'

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