bfs_search_tables
AI agents call bfs_search_tables to retrieve information from Pypi:swiss Statistics without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool searches statistical tables from the Swiss Federal Statistical Office. 'Search' and 'list' operations are inherently read-only with no side effects. No modification, deletion, execution, or financial impact is indicated. The empty description lowers confidence slightly, but the name and context of a public statistics server strongly indicate a read operation.
From the tool's definition Tool name 'bfs_search_tables' combined with sibling tools (bfs_list_tables_by_theme, bfs_list_themes, bfs_get_data, bfs_get_table_metadata) all following a read-only query pattern against a statistical database.
Attacks that exploit this kind of access
bfs_search_tables. It is categorised as a Read tool in the Pypi:swiss Statistics MCP Server, which means it retrieves data without modifying state.
Register the Pypi:swiss Statistics MCP server in PolicyLayer and add a rule for bfs_search_tables: 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 Statistics. Nothing to install.
bfs_search_tables 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 bfs_search_tables 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 bfs_search_tables. 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.
bfs_search_tables is provided by the Pypi:swiss Statistics MCP server (malkreide/swiss-statistics-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 →