bqe_update_ai_check · Phrase MCP: Risk & Policy

WHAT IT DOES

What bqe_update_ai_check does on Phrase

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

WHY IT NEEDS A POLICY

Why bqe_update_ai_check needs a policy

This is classified as Write because the tool creates or modifies data reversibly. It performs a PUT request to update an AI Check configuration, replacing name and qualityRequirements. The blast radius is medium because modifying quality evaluation rules could affect localization workflow and QA processes, but changes are reversible and don't delete data or incur financial obligations.

From the tool's definition Updates an existing AI Check in Phrase Quality Evaluator. Tool uses PUT operation which modifies existing data reversibly (name and qualityRequirements fields can be changed again).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

bqe_update_ai_check Rate-limited

bqe_update_ai_check 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": {
    "bqe_update_ai_check": {
      "limits": [
        {
          "counter": "bqe_update_ai_check_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 Phrase, so you can run agents against it safely.

FAQ

Questions about bqe_update_ai_check

What does the bqe_update_ai_check tool do? +

Update an existing AI Check in Phrase Quality Evaluator. Replaces both name and qualityRequirements. (PUT /v1/aiChecks/{uid}). It is categorised as a Write tool in the Phrase MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on bqe_update_ai_check? +

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

What risk level is bqe_update_ai_check? +

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

Can I rate-limit bqe_update_ai_check? +

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

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

bqe_update_ai_check is provided by the Phrase MCP server (phrase-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.