catalog_run_tool · tin-can MCP: Risk & Policy

WHAT IT DOES

What catalog_run_tool does on tin-canMCP

AI agents invoke catalog_run_tool to trigger actions in tin-canMCP. 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 catalog_run_tool needs a policy

This is a meta-execution tool that dynamically invokes other tools on the MCP server. It functions as a dispatcher or executor that triggers external operations (other catalog tools) based on runtime parameters. The effects are not predetermined and depend on the arguments and target tool selected, making it Execute rather than Write.

From the tool's definition 'Run an active catalog tool by name using manifest-driven argv construction' — the tool executes arbitrary catalog tools with dynamically constructed arguments, enabling execution of operations whose effects depend entirely on which tool is invoked and what…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

catalog_run_tool Rate-limited

catalog_run_tool 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": {
    "catalog_run_tool": {
      "limits": [
        {
          "counter": "catalog_run_tool_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 tin-canMCP, so you can run agents against it safely.

FAQ

Questions about catalog_run_tool

What does the catalog_run_tool tool do? +

Run an active catalog tool by name using manifest-driven argv construction. It is categorised as a Execute tool in the tin-canMCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on catalog_run_tool? +

Register the tin-can MCP server in PolicyLayer and add a rule for catalog_run_tool: 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 tin-canMCP. Nothing to install.

What risk level is catalog_run_tool? +

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

Can I rate-limit catalog_run_tool? +

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

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

catalog_run_tool is provided by the tin-can MCP server (juangrukat/tin-canmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.