AI agents call tms_get_trans_memory 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 queries and retrieves translation memory details from the Phrase TMS system. It has no side effects—it does not create, modify, delete, or execute code. The GET verb and 'Get details' phrasing confirm retrieval semantics. Severity is low because reading translation memory metadata poses minimal risk even if misused by an AI agent.
From the tool's definition Tool description explicitly states 'Get details' and uses GET HTTP method, which retrieves data without modification. Returns translation memory metadata from TMS API endpoint.
Attacks that exploit this kind of access
Get details for a specific Phrase TMS translation memory. (GET /api2/v1/transMemories/{tmUid}). 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 tms_get_trans_memory: 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.
tms_get_trans_memory 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 tms_get_trans_memory 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 tms_get_trans_memory. 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.
tms_get_trans_memory 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 →