AI agents invoke crudTabla to trigger actions in MyPos MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
CRUD encompasses all four database operations including destructive ones (Delete). Since the tool spans multiple categories, the most severe applicable category is chosen. The description is largely uninformative ('Sigue estas reglas OBLIGATORIAS para operaciones CRUD'), but the name and context strongly suggest it can perform irreversible deletions.
From the tool's definition Tool name 'crudTabla' implies Create, Read, Update, Delete operations on a table; server description mentions MySQL/PostgreSQL database access; sibling tools include destructive operations like 'eliminarColumna', 'eliminarClaveForanea'
Attacks that exploit this kind of access
Sigue estas reglas OBLIGATORIAS para operaciones CRUD:\n. It is categorised as a Execute tool in the MyPos MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MyPos MCP server in PolicyLayer and add a rule for crudTabla: 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.
crudTabla is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the crudTabla 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 crudTabla. 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.
crudTabla 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 →