bak_search_isos
AI agents call bak_search_isos to retrieve information from Pypi:swiss Culture without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Search operations on public cultural heritage data retrieve information without side effects. No modification, deletion, code execution, or financial operations are implied. The description is empty, which reduces confidence slightly, but the naming pattern and sibling tools clearly establish this as a read-only query tool.
From the tool's definition Tool name is 'bak_search_isos' which indicates a search operation on ISOS (Inventories of Swiss Cultural Heritage Sites) data.
Attacks that exploit this kind of access
bak_search_isos. It is categorised as a Read tool in the Pypi:swiss Culture MCP Server, which means it retrieves data without modifying state.
Register the Pypi:swiss Culture MCP server in PolicyLayer and add a rule for bak_search_isos: 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:swiss Culture. Nothing to install.
bak_search_isos 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 bak_search_isos 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 bak_search_isos. 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.
bak_search_isos is provided by the Pypi:swiss Culture MCP server (malkreide/swiss-culture-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 →