AI agents call columnasDeTabla to retrieve information from MyPos MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata about table columns from a database. It performs a read-only operation that retrieves or queries data without creating, modifying, deleting, or executing code. The incomplete description ('Sigue estas reglas para listar columnas:\n') does not alter this classification—the function signature clearly indicates column listing/retrieval.
From the tool's definition Tool name 'columnasDeTabla' (columns of table) and context describing 'retrieve column information' indicates a query operation with no side effects.
Attacks that exploit this kind of access
Sigue estas reglas para listar columnas:\n. It is categorised as a Read tool in the MyPos MCP MCP Server, which means it retrieves data without modifying state.
Register the MyPos MCP server in PolicyLayer and add a rule for columnasDeTabla: 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 MyPos MCP. Nothing to install.
columnasDeTabla 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 columnasDeTabla 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 columnasDeTabla. 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.
columnasDeTabla is provided by the MyPos MCP server (yonsn76/mypos-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 →