trigger_run · FullMention MCP: Risk & Policy

WHAT IT DOES

What trigger_run does on FullMention

AI agents invoke trigger_run to trigger actions in FullMention. 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 trigger_run needs a policy

This tool executes a simulation process with arguments that determine its behavior and results. While the simulation itself is described as 'stateless,' triggering a run is an active operation that causes external computation to occur. It does not create persistent data (Write), retrieve only data (Read), delete data (Destructive), or involve financial transactions (Financial).

From the tool's definition Tool description states 'Trigger an asynchronous stateless simulation run' — the verb 'trigger' combined with 'run' indicates the tool executes a computation or process.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

trigger_run Rate-limited

trigger_run 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": {
    "trigger_run": {
      "limits": [
        {
          "counter": "trigger_run_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 FullMention, so you can run agents against it safely.

FAQ

Questions about trigger_run

What does the trigger_run tool do? +

Trigger an asynchronous stateless simulation run for a list of keywords and selected engines. It is categorised as a Execute tool in the FullMention MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on trigger_run? +

Register the FullMention MCP server in PolicyLayer and add a rule for trigger_run: 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 FullMention. Nothing to install.

What risk level is trigger_run? +

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

Can I rate-limit trigger_run? +

Yes. Add a rate_limit block to the trigger_run 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 trigger_run completely? +

Set action: deny in the PolicyLayer policy for trigger_run. 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 trigger_run? +

trigger_run is provided by the FullMention MCP server (riisager/fullmention-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.