run_agent · Spaceship MCP: Risk & Policy

WHAT IT DOES

What run_agent does on Spaceship MCP

AI agents invoke run_agent to trigger actions in Spaceship MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why run_agent needs a policy

This tool triggers external operations (execution of agents) whose effects depend on the agent's configuration and arguments. The actual behavior cannot be fully assessed from code inspection alone, but the context clearly indicates it executes agents, which qualifies as Execute category.

From the tool's definition Tool name is 'run_agent' and server description states it 'provides comprehensive tools for agent lifecycle management, including creation, execution, and real-time monitoring.' The 'run_agent' function directly executes AI agents on the Spaceship platform.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_agent Rate-limited

run_agent stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "run_agent": {
      "limits": [
        {
          "counter": "run_agent_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Spaceship MCP, so you can run agents against it safely.

FAQ

Questions about run_agent

What does the run_agent tool do? +

run_agent. It is categorised as a Execute tool in the Spaceship MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_agent? +

Register the Spaceship MCP server in PolicyLayer and add a rule for run_agent: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Spaceship MCP. Nothing to install.

What risk level is run_agent? +

run_agent is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit run_agent? +

Yes. Add a rate_limit block to the run_agent rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block run_agent completely? +

Set action: deny in the PolicyLayer policy for run_agent. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides run_agent? +

run_agent is provided by the Spaceship MCP server (spaceship-ai/spaceship-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.