epl_ggsl_abfrage
AI agents call epl_ggsl_abfrage to retrieve information from Pypi:bag Epl without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name 'epl_ggsl_abfrage' combines 'abfrage' (German for 'query') with 'ggsl' (likely referring to a specific BAG list for medications/medical devices). There is no indication of write, delete, or execute capabilities. The tool appears designed to retrieve and query official insurance coverage information without modifying data or executing code.
From the tool's definition Tool is part of a medical insurance coverage query system. The server description indicates 'natural language queries about Swiss mandatory health insurance coverage' and sibling tools are named with '_suche' (search) and '_abfrage' (query) suffixes,…
Attacks that exploit this kind of access
epl_ggsl_abfrage. It is categorised as a Read tool in the Pypi:bag Epl MCP Server, which means it retrieves data without modifying state.
Register the Pypi:bag Epl MCP server in PolicyLayer and add a rule for epl_ggsl_abfrage: 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:bag Epl. Nothing to install.
epl_ggsl_abfrage 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 epl_ggsl_abfrage 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 epl_ggsl_abfrage. 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.
epl_ggsl_abfrage is provided by the Pypi:bag Epl MCP server (malkreide/bag-epl-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 →