AI agents call tms_get_analysis 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 tool retrieves read-only data from the Phrase TMS API. It queries analysis metadata without side effects, making it a Read operation. The blast radius is minimal—an agent fetching analysis data cannot modify localization projects, delete content, or trigger external operations.
From the tool's definition Tool description explicitly states 'Fetch a single analysis by UID' and uses GET HTTP method. Returns analysis details (word counts, match rates, associated jobs) with no modification, deletion, or execution of code.
Attacks that exploit this kind of access
Fetch a single analysis by UID from Phrase TMS. Returns analysis details including word counts, match rates, and associated jobs. (GET /api2/v3/analyses/{analyseUid}). 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_analysis: 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_analysis 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_analysis 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_analysis. 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_analysis 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 →