AI agents call list_message_keys to retrieve information from Paraglide without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns message keys from the i18n project without side effects. Filtering by prefix and translation status are read-only query parameters. The blast radius of misuse is minimal—an agent could only retrieve metadata about available messages, not modify or delete data.
From the tool's definition Tool name 'list_message_keys' and description 'List message keys' indicate a retrieval operation with optional filtering by prefix and translation status. No modifications, deletions, or execution of external code.
Attacks that exploit this kind of access
List message keys, optionally filtered by key prefix (startsWith) and by translation. It is categorised as a Read tool in the Paraglide MCP Server, which means it retrieves data without modifying state.
Register the Paraglide MCP server in PolicyLayer and add a rule for list_message_keys: 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 Paraglide. Nothing to install.
list_message_keys 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 list_message_keys 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 list_message_keys. 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.
list_message_keys is provided by the Paraglide MCP server (weshaze/paraglide-mcp). 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 →