AI agents call tms_search_termbase_terms 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.
The tool performs a read-only search operation against a termbase to retrieve matching terms. While it uses POST (typically associated with mutations), the endpoint is explicitly documented as a search function, which is a data retrieval operation with no side effects. There is no evidence of modification, deletion, or execution of arbitrary code.
From the tool's definition Tool name contains 'search' and description explicitly states 'Search for terms within a Phrase TMS termbase' with POST /api2/v1/termBases/{uid}/search endpoint. This is a query operation that retrieves term data without modifying or deleting anything.
Attacks that exploit this kind of access
Search for terms within a Phrase TMS termbase. (POST /api2/v1/termBases/{uid}/search). 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_search_termbase_terms: 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_search_termbase_terms 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_search_termbase_terms 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_search_termbase_terms. 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_search_termbase_terms 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 →