bak_list_traditions
AI agents call bak_list_traditions 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.
The naming convention (bak_list_*) and server purpose (querying Swiss cultural heritage data) strongly suggest this is a read-only retrieval tool that lists or enumerates Living Traditions records. No write, execute, destructive, or financial operations are implied.
From the tool's definition Tool name 'bak_list_traditions' indicates a list/retrieval operation. Description is empty, but the server provides 'Living Traditions' cultural heritage data and context shows sibling tools like 'bak_get_tradition_detail' and 'bak_search_isos' perform…
Attacks that exploit this kind of access
bak_list_traditions. 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_list_traditions: 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_list_traditions 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_list_traditions 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_list_traditions. 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_list_traditions 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 →