AI agents call bqe_list_ai_checks to retrieve information from Phrase without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only operation that retrieves and lists AI Checks from the Phrase Quality Evaluator API. It performs a query (GET request) with no capability to create, modify, or delete data. The blast radius of misuse is minimal—an agent could enumerate AI Checks, but this poses no direct risk to data integrity or operations.
From the tool's definition Tool name 'bqe_list_ai_checks' and description 'List all AI Checks' indicates a retrieval operation. HTTP method is GET with no side effects. Returns data about existing AI Checks without modification.
Attacks that exploit this kind of access
List all AI Checks for the authenticated organization in Phrase Quality Evaluator. AI Checks are reusable quality requirements written in natural language. (GET /v1/aiChecks). It is categorised as a Read tool in the Phrase MCP Server, which means it retrieves data without modifying state.
Register the Phrase MCP server in PolicyLayer and add a rule for bqe_list_ai_checks: 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.
bqe_list_ai_checks is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the bqe_list_ai_checks 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.
Set action: deny in the PolicyLayer policy for bqe_list_ai_checks. 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.
bqe_list_ai_checks 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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →