update_open_questions · Project Brain MCP: Risk & Policy

WHAT IT DOES

What update_open_questions does on Project Brain

AI agents use update_open_questions 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 update_open_questions needs a policy

This tool creates or modifies data reversibly by updating a list of open questions in the engineering memory system. It does not delete data irreversibly (so not Destructive), execute arbitrary code (so not Execute), or involve financial transactions (so not Financial).

From the tool's definition Tool name 'update_open_questions' and description 'Replace the open_questions list' indicate modification of stored data. The verb 'Replace' confirms write/update semantics rather than read-only or destructive operations.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

update_open_questions Rate-limited

update_open_questions 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": {
    "update_open_questions": {
      "limits": [
        {
          "counter": "update_open_questions_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 update_open_questions

What does the update_open_questions tool do? +

Replace the open_questions list. Use to track unresolved questions for future sessions. 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 update_open_questions? +

Register the Project Brain MCP server in PolicyLayer and add a rule for update_open_questions: 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 update_open_questions? +

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

Can I rate-limit update_open_questions? +

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

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

update_open_questions 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.