Follow these steps to run the Scrapezy MCP Server as an agent in the cloud, using Meshagent Rooms, and connect a chatbot that can utilize the included toolset.

1. Set up Environment Variables

You’ll need the following environment variable:

  • SCRAPEZY_API_KEY: your_api_key (Your Scrapezy API key, required.)

2. Install Meshagent CLI

pip install "meshagent[all]"

3. Authenticate with Meshagent CLI

4. Start The MCP Scrapezy Agent as a Service

meshagent service test \
  --room=test \
  --role=agent \
  --image=meshagent/mcp-scrapezy:latest \
  --env MESHAGENT_PORT=8001 \
  --env SCRAPEZY_API_KEY=your_api_key \
  --port="num=8001 path=/webhook liveness=/ type=meshagent.callable" \
  --name=mcp-scrapezy-service
  • This command starts a Meshagent Room with the Scrapezy MCP server deployed in it.
  • Note: Rooms close automatically if inactive.

5. Join the Room with a Chatbot, Enabling the Scrapezy Toolkit

meshagent chatbot join \
  --room=test \
  --agent-name=sample \
  --name=sample \
  --toolkit=mcp-scrapezy
  • This launches a chatbot in the Meshagent Room with access to Scrapezy tools.
  • You can use multiple toolkits with the same agent in a room.
  • The CLI output will include a URL to the Room where you can interact with the agent and tools.

Tools Available

Tools Provided

ToolShort Description
extract-structured-dataExtract structured data from a website.

Tool: extract-structured-data

Extract structured data from a website.

ParameterTypeDescription
promptstringPrompt to extract data from the website
urlstringURL of the website to extract data from

Meshagent and Resources


For more information about the Scrapezy MCP server, see the Scrapezy repo and Docker Hub listing.