openrouter

Start an OpenRouter expert session (advisory only). Pick a configured

SERVERDeliberation SOURCEantonbabenko/deliberation

High RISK CLASS

Category Execute

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/deliberation/openrouter.md

WHAT IT DOES

What openrouter does on Deliberation

AI agents invoke openrouter to trigger actions in Deliberation. 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.

RISK

Why openrouter is rated High

This tool executes a session with external AI models via OpenRouter, which constitutes triggering an external operation. While described as 'advisory only', it still represents code/query execution against third-party services.

From the tool's definition Tool starts an OpenRouter expert session and involves interaction with external models. The phrase 'Start an OpenRouter expert session' indicates triggering an external operation whose effects depend on the session configuration and model selection arguments.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs openrouter safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Deliberation, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For openrouter, this is the rule to start with:

openrouter Rate-limited

openrouter 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": {
    "openrouter": {
      "limits": [
        {
          "counter": "openrouter_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Deliberation, apply this rule, and every openrouter call is checked against it from then on.

FAQ

Questions about openrouter

What does the openrouter tool do? +

Start an OpenRouter expert session (advisory only). Pick a configured. It is categorised as a Execute tool in the Deliberation MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on openrouter? +

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

What risk level is openrouter? +

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

Can I rate-limit openrouter? +

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

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

openrouter is provided by the Deliberation MCP server (antonbabenko/deliberation). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Deliberation, and thousands of servers like it.

This server

All 11 Deliberation tools → High-risk tools on this server →

Across the catalogue

All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →