AI agents call tms_download_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 and exports existing analysis data from Phrase TMS. The GET method and 'download' operation indicate a read-only query with no side effects on the source system. While the data may be sensitive (localization analytics), the action itself is non-destructive retrieval, placing it in the Read category at low severity.
From the tool's definition Tool description states 'Download an analysis file' and uses GET HTTP method, which retrieves data without modification. Supports multiple read-only output formats (CSV, CSV_EXTENDED, LOG, JSON) and saves to local path.
Attacks that exploit this kind of access
Download an analysis file from Phrase TMS in CSV, CSV_EXTENDED, LOG, or JSON format and save it to a local path. (GET /api2/v1/analyses/{analyseUid}/download). 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_download_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_download_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_download_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_download_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_download_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 →