This quick start will guide you through running the Wolfram Alpha MCP server and chatbot in a temporary Meshagent room for testing. When the Meshagent Room closes, both the tool and chatbot are automatically removed.

Required Environment Variables

Steps

  1. Install Meshagent CLI:
    pip install "meshagent[all]"
    
  2. Sign up and authenticate with Meshagent:
  3. Start MCP Wolfram Alpha Service in a Room:
    meshagent service test \
      --room=test \
      --role=agent \
      --image=meshagent/mcp-wolfram-alpha:latest \
      --env="MESHAGENT_PORT=8001" \
      --env="WOLFRAM_API_KEY=your-app-id" \
      --port="num=8001 path=/webhook liveness=/ type=meshagent.callable" \
      --name=mcp-wolfram-alpha-service-test
    
    • Note: This command creates a Meshagent Room with the MCP server available as a callable tool. The room closes when inactive.
  4. Join a Chatbot to the Room:
    meshagent chatbot join \
      --room=test \
      --agent-name=mcp-wolfram-alpha \
      --name=mcp-wolfram-alpha \
      --toolkit=mcp-wolfram-alpha
    
    • This starts a chatbot in the same room, able to use the Wolfram Alpha toolkit.
    • Multiple toolkits can be loaded in the same room.
    • The link to the room will be provided in the CLI output.
  5. Test the Setup:
    • Open the room link in your browser and send a message to the agent. You can interact with the MCP Wolfram Alpha tool directly from the chat.

Project Level Deployment (Persistent Services)

For production use, create persistent services at the project level so the MCP server tools and chatbot appear in every Meshagent project room automatically. This eliminates the need for local/server-side MCP and simplifies onboarding.

Steps

  1. Create a Persistent MCP Wolfram Alpha Service:
    meshagent service create \
      --role=agent \
      --image=meshagent/mcp-wolfram-alpha:latest \
      --env="MESHAGENT_PORT=8001" \
      --env="WOLFRAM_API_KEY=your-app-id" \
      --port="num=8001 path=/webhook liveness=/ type=meshagent.callable" \
      --name=mcp-wolfram-alpha-service
    
  2. Create a Persistent Chatbot Service:
    meshagent service create \
      --image="meshagent/cli:latest" \
      --port="num=9001 path=/agent liveness=/ type=meshagent.callable participant_name=mcp-wolfram-alpha-chatbot" \
      --env="MESHAGENT_PORT=9001" \
      --name="mcp-wolfram-alpha-chatbot-service" \
      --command="meshagent chatbot service --agent-name=mcp-wolfram-alpha-chatbot --toolkit=mcp-wolfram-alpha"
    

Tools Available

Connect your chat repl to Wolfram Alpha computational intelligence.

Available Tools

Tools provided by this ServerShort Description
query-wolfram-alphaUse Wolfram Alpha to answer a question.

Tool Details

Tool: query-wolfram-alpha

Use Wolfram Alpha to answer a question. This tool should be used when you need complex math or symbolic intelligence.
ParametersTypeDescription
querystring

Use this MCP Server

{
  "mcpServers": {
    "wolfram-alpha": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "WOLFRAM_API_KEY",
        "mcp/wolfram-alpha"
      ],
      "env": {
        "WOLFRAM_API_KEY": "your-app-id"
      }
    }
  }
}

Further Reading and Resources


Meshagent and the MCP Wolfram Alpha toolkit make it easy to add advanced computation and symbolic math to any multi-agent room or workflow, securely and at scale, with minimal setup.