AI agents call get_messages 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 retrieves or queries message content without side effects. It matches the Read category definition: 'retrieves or queries data; no side effects (search, list, get, fetch).' The description explicitly states retrieval by keys/prefix with optional filtering, which are read operations typical of i18n message lookup. No data is created, modified, or deleted.
From the tool's definition Tool name 'get_messages' and description 'Retrieve message content by exact keys or by key prefix' indicate data retrieval with no modification.
Attacks that exploit this kind of access
Retrieve message content by exact keys or by key prefix, optionally restricted to. 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 get_messages: 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.
get_messages 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 get_messages 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 get_messages. 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.
get_messages 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 →