AI agents call cercar_pressupostos 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.
The naming pattern ('cercar' = search) and server context strongly suggest this is a read-only query tool for budget information, consistent with the transparency investigation purpose. With an empty description, confidence is moderate. The tool appears designed to retrieve and cross-reference budget data rather than execute code, delete records, or commit financial actions.
From the tool's definition Tool name 'cercar_pressupostos' combines 'cercar' (Catalan: search) with 'pressupostos' (budgets). The description is empty, but the context of a government transparency/anti-corruption server and sibling tools that perform data search and retrieval…
Documented attack patterns abuse exactly the kind of access cercar_pressupostos 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 cercar_pressupostos:
{
"version": "1",
"default": "deny",
"tools": {
"cercar_pressupostos": {}
}
}cercar_pressupostos 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.
cercar_pressupostos. 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 cercar_pressupostos: 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.
cercar_pressupostos 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 cercar_pressupostos 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 cercar_pressupostos. 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.
cercar_pressupostos 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.