Agent Jobs MCP Server

AI Connect MCP Server

An MCP (Model Context Protocol) server that allows AI agents to query and manage jobs in the AI Connect platform.

About AI Connect Jobs

AI Connect Jobs is a robust asynchronous task management system on the AI Connect platform, enabling the creation, monitoring, and execution of jobs across different platforms like Slack and WhatsApp, with support for scheduled execution, automatic retries, and timeout handling. The API provides endpoints to create, list, query, and cancel jobs, allowing developers and external systems to easily integrate asynchronous processing functionalities into their applications, automating complex workflows without the need to implement the entire task management infrastructure.

Features

This MCP Server provides tools for AI agents to:

• 📋 List Jobs: Query all jobs with advanced filtering
• 🔍 Get Specific Job: Retrieve details of a specific job by ID
• ✅ Create Jobs: Create new jobs for immediate or scheduled execution
• ❌ Cancel Jobs: Cancel running or scheduled jobs
• 📊 Monitor Status: Track job status (WAITING, RUNNING, COMPLETED, FAILED, CANCELED)

Technologies

• Node.js with TypeScript
• Model Context Protocol (MCP) by Anthropic
• Zod for schema validation
• AI Connect API for integration with the Agent Jobs system

Installation

NPX (Recommended)

You can run the MCP server directly using npx without installation:

Local Installation

1. Clone the repository:

2. Install dependencies:

3. Configure environment variables (Optional):

The MCP server comes with default values from .env.example, so you can run it without setting any environment variables. However, you must provide an API key for authentication.

Edit the .env file with your credentials:

Important: If no environment variables are provided, the server will use these defaults:

• DEFAULT_ORG_ID: aiconnect
• AICONNECT_API_URL: https://api.aiconnect.cloud/api/v0
• AICONNECT_API_KEY: empty (must be provided for API calls to work)

4. Build the project:

Usage

CLI Usage

The MCP server now supports CLI commands for easy management:

Setting Environment Variables:

Required Environment Variables:

• AICONNECT_API_URL: API endpoint URL (e.g., https://api.aiconnect.cloud/api/v0)
• AICONNECT_API_KEY: Your API authentication key

CLI Command Examples:

Local Development

For local development, you can use npm scripts:

Configuration Options

This MCP server is designed to work out-of-the-box with minimal configuration. It uses a smart fallback system:

1. With environment variables: Full control over all settings
2. Without environment variables: Uses defaults from .env.example
3. Partial configuration: Mix of environment variables and defaults

Default Values (when no env vars are set):

• DEFAULT_ORG_ID: "aiconnect"
• AICONNECT_API_URL: "https://api.aiconnect.cloud/api/v0"
• AICONNECT_API_KEY: "" (empty - you must provide this)

Error Handling:

• The server will always start, even if environment variables are missing.
• If AICONNECT_API_KEY or AICONNECT_API_URL are not provided, each tool will return a clear error message upon execution, guiding the user to configure the environment correctly.
• If DEFAULT_ORG_ID is not set, it defaults to "aiconnect".

Running the MCP server

The server will start and wait for connections via stdio transport.

Claude Desktop Configuration

To use this MCP server with Claude Desktop, add the following configuration to your claude_desktop_config.json file:

Available Tools

🔧 list_jobs

Lists all jobs with filtering and pagination options.

Parameters:

• status (optional): Filter by status (WAITING, RUNNING, COMPLETED, FAILED, CANCELED)
• job_type_id (optional): Filter by job type
• channel_code (optional): Filter by channel code
• limit (optional): Result limit (default: 50)
• offset (optional): Pagination offset
• sort (optional): Field and direction for sorting

🔍 get_job

Gets details of a specific job.

Parameters:

• job_id (required): ID of the job to query

✅ create_job

Creates a new job for execution.

Parameters:

• target_channel: Target channel configuration
• job_type_id: Job type ID
• config: Job configuration (timeouts, retries, etc.)
• params: Job-specific parameters
• scheduled_at (optional): Date/time for scheduled execution
• delay (optional): Random delay in minutes

❌ cancel_job

Cancels a running or scheduled job.

Parameters:

• job_id (required): ID of the job to cancel
• reason (optional): Cancellation reason

Job Status

Jobs can have the following status values:

• WAITING: Job waiting for execution
• SCHEDULED: Job scheduled for future execution
• RUNNING: Job currently running
• COMPLETED: Job completed successfully
• FAILED: Job failed
• CANCELED: Job was canceled

Usage Examples

List running jobs

Query specific job

Create scheduled job

Cancel job

Project Structure

Development

Available scripts

• npm run build: Compiles TypeScript
• npm start: Runs the compiled server

Adding new tools

Adding a new tool is simple:

1. Create a new TypeScript file inside the src/tools/ directory (e.g., my_new_tool.ts).
2. Implement your tool logic following the existing pattern. The server will automatically detect and register it on startup.
3. Recompile the project with npm run build.

Contributing

1. Fork the project
2. Create a feature branch (git checkout -b feature/new-feature)
3. Commit your changes (git commit -am 'Add new feature')
4. Push to the branch (git push origin feature/new-feature)
5. Open a Pull Request

License

This project is licensed under the MIT License.

Support

For technical support or questions about AI Connect Jobs:

• Check the API documentation
• Contact the AI Connect development team

Note: This project was developed using the Anthropic mcp-tools scaffold for integration with the AI Connect platform.