heritage_browse_collection
AI agents call heritage_browse_collection to retrieve information from Pypi:swiss Cultural Heritage without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name indicates retrieval/browsing of collection items from Swiss cultural heritage repositories. No indication of modification, deletion, execution, or financial operations. The empty description reduces confidence, but sibling tools and the server's stated purpose (enabling AI-native access to data) suggest this follows the same read-only pattern.
From the tool's definition Tool name 'heritage_browse_collection' suggests browsing/retrieving collection data. Description is empty, limiting direct confirmation.
Attacks that exploit this kind of access
heritage_browse_collection. It is categorised as a Read tool in the Pypi:swiss Cultural Heritage MCP Server, which means it retrieves data without modifying state.
Register the Pypi:swiss Cultural Heritage MCP server in PolicyLayer and add a rule for heritage_browse_collection: 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 Cultural Heritage. Nothing to install.
heritage_browse_collection 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 heritage_browse_collection 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 heritage_browse_collection. 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.
heritage_browse_collection is provided by the Pypi:swiss Cultural Heritage MCP server (malkreide/swiss-cultural-heritage-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 →