Doit

​

Running an Agent and Tool in the Cloud

1. Set Required Environment Variables:

   • DOIT_API_KEY - (Your DoiT API key)

2. Install Meshagent CLI with all required dependencies:

   Copy

   Ask AI

   pip install "meshagent[all]"
   

3. Sign up and authenticate with Meshagent:

   • Follow instructions at Meshagent CLI Get Started

4. Start the MCP DoiT service in a Meshagent Room:

   Copy

   Ask AI

   meshagent service test \
     --room=test \
     --role=agent \
     --image=meshagent/mcp-doit:latest \
     --env MESHAGENT_PORT=8001 \
     --env DOIT_API_KEY=your_doit_api_key \
     --port="num=8001 path=/webhook liveness=/ type=meshagent.callable" \
     --name=mcp-doit-service
   

   • This command starts the MCP server as an agent in a Meshagent room. Note that rooms close automatically if inactive.

5. Join a chatbot agent to the room to use the toolkit:

   Copy

   Ask AI

   meshagent chatbot join \
     --room=test \
     --agent-name=sample \
     --name=sample \
     --toolkit=mcp-doit
   

   • This starts a chatbot in the room with access to the doit toolkit. You can launch multiple toolkits and agents in the same room for wider workflows.
   • The command output will include a clickable link to interact with the room, agent, and available tools in your browser.

​

Environment Variables Required

• DOIT_API_KEY — Specifies your DoiT MCP API key for connecting to the DoiT backend.

​

Tools Available

​

Tool Details

​

get_anomalies

List anomalies detected in cloud costs

​

get_anomaly

Get a specific anomaly by ID

​

get_cloud_incident

Get a specific cloud incident by ID

​

get_cloud_incidents

Get cloud incidents

​

get_dimension

Get a specific Cloud Analytics dimension by type and ID

​

get_report_results

Get the results of a specific report by ID

​

list_dimensions

Lists Cloud Analytics dimensions that your account has access to. Use this tool to get the dimensions that you can use in the run_query tool. Use filter to narrow down the results.

​

list_reports

Lists Cloud Analytics reports that your account has access to

​

run_query

Runs a report query with the specified configuration without persisting it.

Fields that are not populated will use their default values if needed. Use the dimension tool before running the query to get the list of dimensions and their types. If possible, use timeRange instead of customTimeRange when no specific dates are given.

Example for cost report:

{
  "config": {
    "dataSource": "billing",
    "metric": {"type": "basic", "value": "cost"},
    "timeRange": {"mode": "last", "amount": 1, "unit": "month", "includeCurrent": true},
    "group": [{"id": "service_description", "type": "fixed", "limit": {"metric": {"type": "basic", "value": "cost"}, "sort": "desc", "value": 10}}]
  }
}

​

validate_user

Validates the current API user and returns domain and email information

​

Further Resources

• Meshagent Website: https://www.meshagent.com/
• Getting Started Documentation: https://docs.meshagent.com/room_api/get_started
• Meshagent Room API Overview: https://docs.meshagent.com/room_api/overview
• Meshagent MCP DoiT Tool Image: https://hub.docker.com/r/meshagent/mcp-doit