Here’s how to get running in a temporary Room for Cloud-based testing:

Prerequisites

  • Python, Docker, and Meshagent CLI installed
  • Sign up and authenticate with Meshagent

Environment Variables

  • SUZIEQ_API_ENDPOINT=<replace-with-your-endpoint>
  • SUZIEQ_API_KEY=<replace-with-your-api-key>

Steps

  1. Install Meshagent (with all features):
    pip install "meshagent[all]"
    
  2. Authenticate with Meshagent: Follow instructions at Meshagent CLI Getting Started.
  3. Start MCP Server as an Agent in a Meshagent Room:
    meshagent service test \
      --room=test \
      --role=agent \
      --image=meshagent/mcp-suzieq-mcp:latest \
      --env MESHAGENT_PORT=8001 \
      --env SUZIEQ_API_ENDPOINT=<your-endpoint> \
      --env SUZIEQ_API_KEY=<your-api-key> \
      --port="num=8001 path=/webhook liveness=/ type=meshagent.callable" \
      --name=mcp-suzieq-mcp-service-test
    
    This starts a Room called test with your MCP Server running inside. If inactive, the Room and its agents will be deleted automatically.
  4. Start a Chatbot in the Same Room with the Suzieq MCP Toolkit:
    meshagent chatbot join \
      --room=test \
      --agent-name=mcp-suzieq-mcp \
      --name=mcp-suzieq-mcp \
      --toolkit=mcp-suzieq-mcp
    
    • The CLI outputs a link to the Room when the chatbot joins.
    • Multiple toolkits can be attached to the same agent.
  5. Use the Room:
    • Visit the output link in your browser.
    • Send a message to the agent to interact with Suzieq MCP server tools.

Project Level Deployment

Deploy the MCP Server and Chatbot as persistent project-level services—making them automatically available in every Room created in your Meshagent project (perfect for production).
  1. Create MCP Server Agent Service:
    meshagent service create \
      --role=agent \
      --image=meshagent/mcp-suzieq-mcp:latest \
      --env MESHAGENT_PORT=8001 \
      --env SUZIEQ_API_ENDPOINT=<your-endpoint> \
      --env SUZIEQ_API_KEY=<your-api-key> \
      --port="num=8001 path=/webhook liveness=/ type=meshagent.callable" \
      --name=mcp-suzieq-mcp-service
    
  2. Create Chatbot Service with MCP Toolkit:
    meshagent service create \
      --image="meshagent/cli:latest" \
      --port="num=9001 path=/agent liveness=/ type=meshagent.callable participant_name=mcp-suzieq-mcp-chatbot" \
      --env="MESHAGENT_PORT=9001" \
      --name="mcp-suzieq-mcp-chatbot-service" \
      --command="meshagent chatbot service --agent-name=mcp-suzieq-mcp-chatbot --toolkit=mcp-suzieq-mcp"
    
  • Now, each time a Room is created in your project, both the MCP server and toolkit chatbot join automatically. No need to run them locally or launch them separately.

Tools Available

MCP Server to interact with a SuzieQ network observability instance via its REST API.

Tools Provided

Tool NameShort Description
run_suzieq_showRuns a SuzieQ ‘show’ query via its REST API.
run_suzieq_summarizeRuns a SuzieQ ‘summarize’ query via its REST API.

Tool Details

run_suzieq_show

Description: Runs a SuzieQ ‘show’ query via its REST API.
ParameterTypeDescription
tablestringThe name of the SuzieQ table to query (e.g., ‘device’, ‘bgp’, ‘interface’, ‘route’).
filtersstring (optional)An optional dictionary of filter parameters for the SuzieQ query.

run_suzieq_summarize

Description: Runs a SuzieQ ‘summarize’ query via its REST API.
ParameterTypeDescription
tablestringThe name of the SuzieQ table to summarize (e.g., ‘device’, ‘bgp’, ‘interface’, ‘route’).
filtersstring (optional)An optional dictionary of filter parameters for the SuzieQ query.

Resources

Happy networking!