llm_chat · LLM MCP Bridge MCP: Risk & Policy

WHAT IT DOES

What llm_chat does on LLM MCP Bridge

AI agents invoke llm_chat to trigger actions in LLM MCP Bridge. 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 llm_chat needs a policy

This tool triggers an external operation by sending prompts to an LLM API (local or cloud) and executing inference. It is not purely a read operation since it actively invokes a remote/local model computation.

From the tool's definition 'Envía un prompt al modelo y recibe una respuesta' — sends a prompt to an LLM model and receives a response with performance metrics (latency, tokens/s)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

llm_chat Rate-limited

llm_chat 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": {
    "llm_chat": {
      "limits": [
        {
          "counter": "llm_chat_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 LLM MCP Bridge, so you can run agents against it safely.

FAQ

Questions about llm_chat

What does the llm_chat tool do? +

Envía un prompt al modelo y recibe una respuesta con métricas de rendimiento (latencia, tokens/s). It is categorised as a Execute tool in the LLM MCP Bridge MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on llm_chat? +

Register the LLM MCP Bridge MCP server in PolicyLayer and add a rule for llm_chat: 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 LLM MCP Bridge. Nothing to install.

What risk level is llm_chat? +

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

Can I rate-limit llm_chat? +

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

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

llm_chat is provided by the LLM MCP Bridge MCP server (ramgeart/llm-mcp-bridge). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.