Agent.Ai MCP Server

# Agent.ai MCP Server An MCP server implementation that integrates with the Agent.ai API, providing web text extraction, web screenshots, and YouTube

Local serverstdio

What is the Agent.Ai MCP server?

Agent.Ai MCP server exists for a simple reason — assistants are far more useful when they can act on Agent.Ai directly instead of describing what you should do. # Agent.ai MCP Server An MCP server implementation that integrates with the Agent.ai API, providing web text extraction, web screenshots, and YouTube transcript capabilities through a dynamic function loading system. ## Features -.

What you get

  • Dynamic Function Loading — Automatically fetches available functions from Agent.ai API
  • Web Text Extraction — Scrape or crawl web pages for text content
  • Web Screenshots — Capture visual screenshots of web pages
  • YouTube Transcripts — Extract transcripts from YouTube videos
  • Caching — Efficient caching of function definitions to reduce API calls

Setting it up

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.

What the assistant can call

Once Agent.Ai is connected, these are the calls the assistant has available:

  • grab_web_text — Extract text content from web pages
  • Inputs — - url (string, required): URL of the web page to extract
  • grab_web_screenshot — Capture visual screenshots of web pages
  • get_youtube_transcript — Fetch transcripts from YouTube videos

Configuration and credentials

You will need one environment variable: API_TOKEN. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the agent.ai mcp server does with a few real requests.

Choosing this one

This sits in the cloud and infrastructure group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Agent.Ai's toolset — grab_web_text, Inputs, grab_web_screenshot and 1 more — is a fair guide to whether it matches your workflow. It is maintained by OnStartups; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Agent.Ai's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Available tools

ToolWhat it does
grab_web_textExtract text content from web pages
Inputs- url (string, required): URL of the web page to extract
grab_web_screenshotCapture visual screenshots of web pages
get_youtube_transcriptFetch transcripts from YouTube videos

How to install the Agent.Ai MCP server

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

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
API_TOKENCredential the server authenticates with.Yes

Example prompts to try

  • Use Agent.Ai to grab web text.
  • Use Agent.Ai to Inputs.
  • Use Agent.Ai to grab web screenshot.

Frequently asked questions

It acts as a bridge between MCP-compatible clients (like Claude Desktop) and the Agent.ai API, allowing you to call Agent.ai tools – such as web scraping, screenshots, and YouTube transcript extraction – directly from your AI assistant.