AI agents call llistar_camps to retrieve information from Mcp Govern without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool is a metadata query that lists available column names or field definitions in a dataset. It does not retrieve actual data, modify anything, execute code, or cause destructive changes. It is a Read operation—specifically a schema/structure inspection with low severity and low blast radius if misused by an AI agent.
From the tool's definition Tool name 'llistar_camps' (list fields/columns) and description 'Retorna els camps disponibles d'un dataset' (Returns the available fields of a dataset) indicate a purely informational, schema-inspection operation with no data retrieval or side effects.
Documented attack patterns abuse exactly the kind of access llistar_camps gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Govern, and nothing reaches the server without passing your rules. This is the rule we recommend for llistar_camps:
{
"version": "1",
"default": "deny",
"tools": {
"llistar_camps": {}
}
}llistar_camps is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Retorna els camps disponibles d'un dataset. It is categorised as a Read tool in the Mcp Govern MCP Server, which means it retrieves data without modifying state.
Register the Mcp Govern MCP server in PolicyLayer and add a rule for llistar_camps: 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 Mcp Govern. Nothing to install.
llistar_camps 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 llistar_camps 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 llistar_camps. 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.
llistar_camps is provided by the Mcp Govern MCP server (xavimf87/mcp-govern). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcp Govern, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
49 Mcp Govern tools catalogued and risk-classified — across an index of 43,000+ MCP servers.