generate_adr · Adr Skills MCP: Risk & Policy

WHAT IT DOES

What generate_adr does on Adr Skills

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

WHY IT NEEDS A POLICY

Why generate_adr needs a policy

This tool creates new Architecture Decision Records (markdown files) based on session analysis. Creation of new documents is a Write operation—reversible (files can be edited or deleted later). Severity is medium because ADRs influence architectural decisions and incorrect auto-generated records could mislead teams, but the content is human-reviewable before adoption and the operation is not destructive or financial.

From the tool's definition Tool description states it 'auto-generate[s] an ADR' and 'Exports a markdown file', indicating creation of new data artifacts. The name 'generate_adr' and phrase 'Analyze a saved session and auto-generate' confirm content generation.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

generate_adr Rate-limited

generate_adr 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_adr": {
      "limits": [
        {
          "counter": "generate_adr_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 Adr Skills, so you can run agents against it safely.

FAQ

Questions about generate_adr

What does the generate_adr tool do? +

Analyze a saved session and auto-generate an ADR. Exports a markdown file and warns about similar past decisions. It is categorised as a Write tool in the Adr Skills 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_adr? +

Register the Adr Skills MCP server in PolicyLayer and add a rule for generate_adr: 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 Adr Skills. Nothing to install.

What risk level is generate_adr? +

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

Can I rate-limit generate_adr? +

Yes. Add a rate_limit block to the generate_adr 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_adr completely? +

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

generate_adr is provided by the Adr Skills MCP server (wooxogh/adr-mcp-setup). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.