descubrir_columnas
AI agents call descubrir_columnas to retrieve information from Pagila MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name translates to 'discover columns', which strongly implies a schema introspection/read operation. The server is explicitly described as read-only, and sibling tools are all query/read oriented. Empty description lowers confidence slightly, but context strongly supports a Read classification.
From the tool's definition Tool name 'descubrir_columnas' (discover columns) on a self-described read-only MCP server for querying a PostgreSQL database. Sibling tools include 'descubrir_tablas' (discover tables), suggesting schema discovery operations.
Attacks that exploit this kind of access
descubrir_columnas. It is categorised as a Read tool in the Pagila MCP MCP Server, which means it retrieves data without modifying state.
Register the Pagila MCP server in PolicyLayer and add a rule for descubrir_columnas: 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 Pagila MCP. Nothing to install.
descubrir_columnas 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 descubrir_columnas 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 descubrir_columnas. 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.
descubrir_columnas is provided by the Pagila MCP server (lyrken/pagila_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 →