record_architectural_decision · BLUEPRINT MCP: Risk & Policy

WHAT IT DOES

What record_architectural_decision does on BLUEPRINT MCP

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

WHY IT NEEDS A POLICY

Why record_architectural_decision needs a policy

This tool creates and writes a new Architectural Decision Record (ADR) file to the repository's .blueprint/decisions/ directory. This is a reversible write operation (files can be deleted or overridden), not destructive. Misuse could introduce misleading architectural guidance that affects future AI agent decisions, giving it a medium severity blast radius.

From the tool's definition Record an ADR under .blueprint/decisions/ for long-term architectural continuity

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

record_architectural_decision Rate-limited

record_architectural_decision 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": {
    "record_architectural_decision": {
      "limits": [
        {
          "counter": "record_architectural_decision_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 BLUEPRINT MCP, so you can run agents against it safely.

FAQ

Questions about record_architectural_decision

What does the record_architectural_decision tool do? +

Record an ADR under .blueprint/decisions/ for long-term architectural continuity. It is categorised as a Write tool in the BLUEPRINT 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 record_architectural_decision? +

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

What risk level is record_architectural_decision? +

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

Can I rate-limit record_architectural_decision? +

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

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

record_architectural_decision is provided by the BLUEPRINT MCP server (vedv7/blueprint.mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.