search_table
AI agents call search_table to retrieve information from Datasette MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite the empty tool description, the context strongly indicates this is a data retrieval operation. The server is explicitly read-only, and search_table follows the naming pattern of other read operations (list, describe). Searching/querying a table retrieves data without side effects.
From the tool's definition Tool name 'search_table' combined with server description stating 'read-only access to Datasette instances' and sibling tools (describe_database, execute_sql, list_databases, list_instances) that are all query/exploration operations.
Attacks that exploit this kind of access
search_table. It is categorised as a Read tool in the Datasette MCP MCP Server, which means it retrieves data without modifying state.
Register the Datasette MCP server in PolicyLayer and add a rule for search_table: 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 Datasette MCP. Nothing to install.
search_table 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 search_table 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 search_table. 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.
search_table is provided by the Datasette MCP server (mhalle/datasette-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 →