AI agents call search_crs to retrieve information from Epsg without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries coordinate reference system metadata based on user-supplied search criteria. It has no side effects, does not modify data, execute code, or trigger external operations. It is a pure read operation returning informational results about CRS systems.
From the tool's definition Tool performs search/query operations on CRS database: 'Search EPSG Coordinate Reference Systems (CRS) by keyword', 'Searchable by EPSG code, name, region name, or prefecture name'.
Attacks that exploit this kind of access
Search EPSG Coordinate Reference Systems (CRS) by keyword. Searchable by EPSG code, name, region name, or prefecture name. Covers Japanese JGD2011 CRS family, global WGS84, Web Mercator, and more. It is categorised as a Read tool in the Epsg MCP Server, which means it retrieves data without modifying state.
Register the Epsg MCP server in PolicyLayer and add a rule for search_crs: 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 Epsg. Nothing to install.
search_crs 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 search_crs 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 search_crs. 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.
search_crs is provided by the Epsg MCP server (shuji-bonji/epsg-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 →