TimeLooker

Provides automated search monitoring with AI-based duplicate detection and automatic x402 payments for task creation.

python

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "fortnightly-devs-mcp-x402-task-scheduler": {
      "command": "python",
      "args": [
        "run_mcp_server.py"
      ],
      "env": {
        "PRIVATE_KEY": "your_ethereum_private_key_here",
        "DATABASE_URL": "sqlite:///timelooker.db",
        "OPENAI_API_KEY": "your_openai_api_key_here",
        "PAY_TO_ADDRESS": "0x671cE47E4F38051ba3A990Ba306E2885C2Fe4102",
        "TASK_MANAGER_API_URL": "http://localhost:8000"
      }
    }
  }
}

You run a TimeLooker MCP Server that automates search monitoring, uses AI-powered duplicate detection to identify genuinely new content, and processes payments automatically when you create new tasks. This server lets you configure flexible search tasks, run checks on a schedule, and receive structured email notifications for new items.

How to use

You interact with the MCP server through the MCP client tools. Create a monitoring task for a search query, then run executions to fetch results and review history. You can preview searches before creating tasks, list all your active tasks, check detailed task status, deactivate tasks, and receive email notifications when new items are found. Payments are handled automatically when you create a new task, while all other operations remain free.

How to install

Prerequisites: Python is installed on your system. You will also need access to a database (SQLite is supported) and network connectivity to reach external AI services if you enable AI-powered features.

Step 1: Prepare the environment

Install Python dependencies and the MCP server components.
Ensure you have a private key and a payment address for x402 integration on the base-sepolia network.

Step 2: Start the MCP server locally

Run the MCP server entry point to start listening for client requests.
Typical start command (from the local setup):
python run_mcp_server.py
or, if you prefer an alternative runner: uv run run_mcp_server.py
Ensure the server starts successfully and logs indicate it is listening for connections.

Step 3: Start the API server (for task management and x402 integration)

Run the API server entry point:
python run_api_server.py
or, if you prefer an alternative runner: uv run run_api_server.py
Verify the API is reachable at the configured URL (for example http://localhost:8000 by default).
The API server handles task creation, listing, and execution records along with the x402 payment middleware.

Additional configuration and notes

Configure environment variables to enable payment, API access, and AI features. A typical configuration includes the payment address, private key, API keys for AI services, and a database URL. Use a local SQLite database for development or switch to a PostgreSQL database in production.

Available tools

create_search_task

Create automated monitoring tasks for any search query with optional payment for task creation. Supports cloud mode (Lambda) or local mode for task setup.

execute_search

Execute a search for an existing task to retrieve new results and update the history.

list_search_tasks

List all active monitoring tasks with their current status and configuration.

get_task_status

Retrieve detailed status and recent execution history for a given task.

delete_search_task

Deactivate and remove a monitoring task from active tracking.

search_preview

Preview potential search results for a query without creating a task.

Built by

VeilStrat

AI signals for GTM teams