generate_spec · Reviewer MCP: Risk & Policy

WHAT IT DOES

What generate_spec does on Reviewer MCP

AI agents use generate_spec to create or update resources in Reviewer MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Reviewer MCP environment.

WHY IT NEEDS A POLICY

Why generate_spec needs a policy

This tool creates and writes specification documents, which is a reversible write operation. While it doesn't delete data or execute arbitrary code, it does generate and persist new artifacts.

From the tool's definition Tool is described as 'Generate a specification document', which creates new content (a specification document) that is written/stored.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

generate_spec Rate-limited

generate_spec stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "generate_spec": {
      "limits": [
        {
          "counter": "generate_spec_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Reviewer MCP, so you can run agents against it safely.

FAQ

Questions about generate_spec

What does the generate_spec tool do? +

Generate a specification document using OpenAI O3 model. It is categorised as a Write tool in the Reviewer MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on generate_spec? +

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

What risk level is generate_spec? +

generate_spec is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit generate_spec? +

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

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

generate_spec is provided by the Reviewer MCP server (jaggederest/mcp_reviewer). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.