Start a Control Plane mission — a structured, observable orchestration that runs on APIClaw
AI agents invoke start_mission to trigger actions in APIClaw. 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.
This tool triggers execution of a mission/orchestration on the APIClaw platform. The effects are dependent on what the mission does (which could range from benign to harmful), and once started, the mission runs autonomously. This is fundamentally an Execute category tool because it initiates and triggers external operations. It is not Destructive because missions are presumably reversible or stoppable.
From the tool's definition Tool description states it 'starts' a 'Control Plane mission — a structured, observable orchestration that runs on APIClaw'.
Documented attack patterns abuse exactly the kind of access start_mission gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and APIClaw, and nothing reaches the server without passing your rules. This is the rule we recommend for start_mission:
{
"version": "1",
"default": "deny",
"tools": {
"start_mission": {
"limits": [
{
"counter": "start_mission_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}start_mission 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.
Free to start. No card required.
Start a Control Plane mission — a structured, observable orchestration that runs on APIClaw. It is categorised as a Execute tool in the APIClaw MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the APIClaw MCP server in PolicyLayer and add a rule for start_mission: 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 APIClaw. Nothing to install.
start_mission is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the start_mission 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.
Set action: deny in the PolicyLayer policy for start_mission. 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.
start_mission is provided by the APIClaw MCP server (nordsym/apiclaw). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from APIClaw, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
24 APIClaw tools catalogued and risk-classified — across an index of 43,000+ MCP servers.