swisstopo_search_layers
AI agents call swisstopo_search_layers to retrieve information from Pypi:swisstopo without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name strongly suggests querying or listing layers—a read-only operation. The description is empty, which lowers confidence slightly, but the consistent pattern of sibling tools (all fetch/query operations) and the context of a geodata server support Read classification. No indication of side effects, code execution, data modification, or deletion.
From the tool's definition Tool name 'swisstopo_search_layers' indicates a search/query operation on layer metadata. Sibling tools like 'swisstopo_find_features', 'swisstopo_get_collection', and 'swisstopo_get_feature' are all Read operations querying geodata.
Attacks that exploit this kind of access
swisstopo_search_layers. It is categorised as a Read tool in the Pypi:swisstopo MCP Server, which means it retrieves data without modifying state.
Register the Pypi:swisstopo MCP server in PolicyLayer and add a rule for swisstopo_search_layers: 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 Pypi:swisstopo. Nothing to install.
swisstopo_search_layers 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 swisstopo_search_layers 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 swisstopo_search_layers. 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.
swisstopo_search_layers is provided by the Pypi:swisstopo MCP server (malkreide/swisstopo-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 →