Skip to main content
The Asteroid MCP server lets you manage agents, inspect executions, and update workflows directly from AI-powered coding tools like Claude Code and Cursor. Instead of switching between your editor and the Asteroid platform UI, you can ask your assistant to do it in natural language.

​
What is MCP?

The Model Context Protocol (MCP) is an open standard that connects AI assistants to external tools and data sources. When you add the Asteroid MCP server to your editor, your assistant gains access to Asteroid’s API — it can start executions, read results, update workflows, and more.

​
What You Can Do

Inspect Executions

View execution status, results, and activity logs without leaving your editor.

Manage Workflows

Fetch, modify, and publish agent workflows through natural language commands.

Start Executions

Kick off agent runs with custom inputs directly from your terminal.

Debug Failures

Investigate failed executions by examining outcomes, reasoning, and activity traces.

​
Available Tools

The MCP server exposes the following tools to your AI assistant:
ToolDescription
getContextGet your user context including organization IDs. Call this first.
listAgentsList all agents in your organization.
listAvailableToolsList all available tools/capabilities for AI Task nodes in workflows.
getExecutionFetch the full state of an execution — status, outcome, reasoning, and result.
listExecutionsList executions with filters (agent, status, date range, metadata).
executeAgentStart a new agent execution with custom inputs.
getExecutionActivitiesFetch the activity log for an execution (tool calls, messages, events).
getWorkflowRetrieve the current published workflow for an agent.
createWorkflowCreate a new workflow version.
publishWorkflowPublish a workflow version to make it the active version.
The MCP server uses your Asteroid API key for authentication. All actions respect the same permissions as the platform UI and REST API.

​
Quick Start

  1. Set up the MCP server in Claude Code or Cursor.
  2. Ask your assistant to call getContext to get your organization ID.
  3. Use listAgents to find your agent, then getWorkflow to read its workflow.
  4. Modify the workflow and use createWorkflow + publishWorkflow to deploy changes.
  5. Run executeAgent to test, and getExecution / getExecutionActivities to debug.
See the Setup guide for detailed installation instructions.