Close the Loop With the Upgraded Mastra CLI

Your coding agent can already write Mastra code. Now it can help operate Mastra projects too.

The upgraded Mastra CLI gives coding agents a direct way to invoke agents, run workflows, execute tools, inspect memory, run evals, query traces and logs, manage environments, and deploy updates.

This release expands Mastra's coding-agent tooling alongside Mastra skills and the MCP docs server.

Together, your coding agent can drive the full Mastra workflow without checking in. For example:

• Test an agent with different prompts, review the results, and suggest improvements
• Pull recent traces, find patterns, and turn interesting cases into a new dataset
• Inspect logs and traces after a change, then deploy a fix

Get started

Install the CLI:

npm install mastra@latest -g

Runtime

Runtime commands hit a running Mastra server via --url and can be used to invoke agents, run workflows, execute tools, or list and inspect MCP servers.

mastra api --url http://localhost:4111 agent run weather-agent '{"messages":"What is the weather in London?"}'
mastra api --url http://localhost:4111 workflow run start weather-workflow '{"inputData":{"city":"London"}}'
mastra api --url http://localhost:4111 tool execute get-weather '{"location":"London"}'
mastra api --url http://localhost:4111 mcp list

For production, swap --url to a deployed URL, for example: https://acme.com/api.

Memory

Memory commands can be used to create memory threads, search long-term memory, and read working memory.

mastra api thread create '{"agentId":"weather-agent","resourceId":"user_123","title":"Support conversation"}'
mastra api memory search '{"agentId":"weather-agent","resourceId":"user_123","searchQuery":"London weather","limit":10}'
mastra api memory current get '{"threadId":"thread_abc123","agentId":"weather-agent"}'

Evals

Eval commands are used to create datasets, run experiments, and read results to verify changes.

mastra api dataset create '{"name":"weather-eval"}'
mastra api experiment run <dataset-id> '{"name":"baseline"}'
mastra api experiment results <dataset-id> <experiment-id>

Observability

Observability commands query traces, logs, scores, and metrics across your platform projects using MASTRA_PLATFORM_ACCESS_TOKEN and MASTRA_PROJECT_ID from .env.

mastra api trace list
mastra api log list
mastra api score list
mastra api metric aggregate '{"name":["mastra_model_total_output_tokens"],"aggregation":"sum"}'

See observability on Mastra platform for setup instructions.

Platform

Platform commands ship a project, manage environment variables, control the running instance, and diagnose failed deploys.

mastra studio deploy --yes
mastra server env pull > .env.production
mastra server restart
mastra studio deploy suggestions <deploy-id>

Project

Project commands lint and validate code before shipping, run database migrations, and manage authentication.

mastra lint --preflight
mastra migrate -y
mastra auth login

For more information and full setup instructions, see:

• CLI commands reference
• mastra api reference
• Build with AI