fedlex_search_treaties
AI agents call fedlex_search_treaties to retrieve information from Pypi:fedlex without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves treaty information from Swiss federal law databases. Search operations are inherently read-only with no capability to modify, delete, or execute actions. The empty description lowers confidence slightly, but the naming convention and server purpose make the Read category appropriate with high confidence. No data modification, deletion, or external execution occurs.
From the tool's definition Tool name 'fedlex_search_treaties' indicates a search operation. The server description emphasizes 'search the SR, monitor legal changes, and query BBl/treaties,' positioning this as a read-only query tool.
Attacks that exploit this kind of access
fedlex_search_treaties. It is categorised as a Read tool in the Pypi:fedlex MCP Server, which means it retrieves data without modifying state.
Register the Pypi:fedlex MCP server in PolicyLayer and add a rule for fedlex_search_treaties: 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:fedlex. Nothing to install.
fedlex_search_treaties 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 fedlex_search_treaties 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 fedlex_search_treaties. 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.
fedlex_search_treaties is provided by the Pypi:fedlex MCP server (malkreide/fedlex-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 →