AI agents call strings_get_glossary 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 queries and retrieves glossary/term base data from Phrase Strings without modifying, deleting, or executing operations. It has no side effects and represents a standard read operation on localization metadata. The low severity reflects minimal blast radius — an agent could only access existing glossary information.
From the tool's definition Tool name and description: 'Get a single term base (previously: glossary)' — the verb 'Get' combined with 'retrieve a single' resource indicates data retrieval only.
Attacks that exploit this kind of access
Get a single term base (previously: glossary) in Phrase Strings. 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 strings_get_glossary: 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.
strings_get_glossary 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 strings_get_glossary 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 strings_get_glossary. 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.
strings_get_glossary 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 →