add_mistake · Project Brain MCP: Risk & Policy

WHAT IT DOES

What add_mistake does on Project Brain

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

WHY IT NEEDS A POLICY

Why add_mistake needs a policy

This tool creates or modifies data (adding mistake records) in a reversible manner. It does not delete data (Destructive), execute arbitrary code (Execute), move money (Financial), or cause irreversible damage. While the system stores engineering decisions that could influence project direction, the tool itself simply writes mistake records.

From the tool's definition 'add_mistake' creates new entries in an engineering memory system ('Add' prefix indicates creation). The sibling tools include 'delete_entry' and 'update_entry', confirming this is a write-capable system.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

add_mistake Rate-limited

add_mistake 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": {
    "add_mistake": {
      "limits": [
        {
          "counter": "add_mistake_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 Project Brain, so you can run agents against it safely.

FAQ

Questions about add_mistake

What does the add_mistake tool do? +

Call this immediately when a mistake or wrong approach is identified. It is categorised as a Write tool in the Project Brain MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on add_mistake? +

Register the Project Brain MCP server in PolicyLayer and add a rule for add_mistake: 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 Project Brain. Nothing to install.

What risk level is add_mistake? +

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

Can I rate-limit add_mistake? +

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

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

add_mistake is provided by the Project Brain MCP server (pym2282/project-brain-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.