invoke_heroku_model_llm

WHAT IT DOES

What invoke_heroku_model_llm does on Agentforce MCP Integration Server

AI agents invoke invoke_heroku_model_llm to trigger actions in Agentforce MCP Integration Server. 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 invoke_heroku_model_llm needs a policy

This tool executes arbitrary prompts against an external LLM service, which constitutes code execution whose effects depend entirely on the prompt arguments. While not directly destructive or financial, the ability to invoke an LLM with attacker-controlled input can trigger unintended downstream actions, data exfiltration, or logical errors.

From the tool's definition Tool name 'invoke_heroku_model_llm' and description 'Invoke the Heroku-hosted LLM to get a response based on the user prompt' indicates execution of an external LLM service with user-supplied prompts, triggering code execution on a remote system.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

invoke_heroku_model_llm Rate-limited

invoke_heroku_model_llm 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": {
    "invoke_heroku_model_llm": {
      "limits": [
        {
          "counter": "invoke_heroku_model_llm_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 Agentforce MCP Integration Server, so you can run agents against it safely.

FAQ

Questions about invoke_heroku_model_llm

What does the invoke_heroku_model_llm tool do? +

Invoke the Heroku-hosted LLM to get a response based on the user prompt. It is categorised as a Execute tool in the Agentforce MCP Integration Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on invoke_heroku_model_llm? +

Register the Agentforce MCP Integration Server MCP server in PolicyLayer and add a rule for invoke_heroku_model_llm: 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 Agentforce MCP Integration Server. Nothing to install.

What risk level is invoke_heroku_model_llm? +

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

Can I rate-limit invoke_heroku_model_llm? +

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

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

invoke_heroku_model_llm is provided by the Agentforce MCP Integration Server MCP server (santhoshsantomcp/mcpnewtest). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.