AI agents invoke chat_with_model to trigger actions in OpenRouter MCP 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.
Based on the server context (OpenRouter unified API for AI models) and sibling tools like 'free_chat' and 'chat_with_vision', this tool likely sends messages to an AI model and retrieves a response. This constitutes an external operation/API call. With no description, confidence is reduced.
From the tool's definition Tool name is 'chat_with_model'; description is empty or uninformative.
Documented attack patterns abuse exactly the kind of access chat_with_model gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and OpenRouter MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for chat_with_model:
{
"version": "1",
"default": "deny",
"tools": {
"chat_with_model": {
"limits": [
{
"counter": "chat_with_model_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}chat_with_model 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.
chat_with_model. It is categorised as a Execute tool in the OpenRouter MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the OpenRouter MCP Server MCP server in PolicyLayer and add a rule for chat_with_model: 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 OpenRouter MCP Server. Nothing to install.
chat_with_model 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 chat_with_model 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 chat_with_model. 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.
chat_with_model is provided by the OpenRouter MCP Server MCP server (physics91/openrouter-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from OpenRouter MCP Server, 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.
9 OpenRouter MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.