Agent.ai

Provides web text extraction, web screenshots, and YouTube transcripts by dynamically loading Agent.ai tools.

typescript

4

GitHub Stars

typescript

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": {
    "onstartups-agentai-mcp-server": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "API_TOKEN",
        "mcp/agentai"
      ],
      "env": {
        "API_TOKEN": "YOUR_API_TOKEN_HERE"
      }
    }
  }
}

Agent.ai MCP Server lets you run a dedicated MCP server that loads capabilities from the Agent.ai API to extract web text, take web screenshots, and fetch YouTube transcripts. It enables you to access powerful web data tasks through a simple MCP client setup, with flexible deployment options and automatic tool discovery.

How to use

You load the Agent.ai MCP Server into your environment and connect to it with an MCP client. The server exposes a set of web-related tools you can invoke from your client, such as grabbing page text, capturing screenshots, and obtaining YouTube transcripts. Tools are discovered dynamically, so new capabilities become available without changing your client.

How to install

Prerequisites vary by how you choose to run the server. You can run it via Docker or via a local MCP server command with NPX. Ensure you have the required runtime on your system before proceeding.

Additional notes

API token security: you must provide an Agent.ai API token to run the MCP server. Keep this token secure and do not expose it in client code or public repositories.

Available tools

grab_web_text

Extracts text content from web pages and supports two modes: scrape for a single page or crawl for up to 100 pages.

grab_web_screenshot

Captures visual screenshots of web pages and can cache results with a time-to-live value.

get_youtube_transcript

Fetches transcripts from YouTube videos given a video URL.