ml_detalhe_anuncio
AI agents call ml_detalhe_anuncio to retrieve information from Mcp Brazil Marketplaces without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to retrieve detailed information about a specific ad from Mercado Livre Brasil. This is a read-only operation with no side effects—it queries and returns existing public data. No data modification, deletion, code execution, or financial operations are implied. The empty description lowers confidence slightly, but the naming pattern and sibling context strongly indicate this is a retrieval tool.
From the tool's definition Tool name 'ml_detalhe_anuncio' contains 'detalhe' (detail/details), indicating retrieval of ad details from Mercado Livre Brasil.
Attacks that exploit this kind of access
ml_detalhe_anuncio. It is categorised as a Read tool in the Mcp Brazil Marketplaces MCP Server, which means it retrieves data without modifying state.
Register the Mcp Brazil Marketplaces MCP server in PolicyLayer and add a rule for ml_detalhe_anuncio: 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 Brazil Marketplaces. Nothing to install.
ml_detalhe_anuncio 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 ml_detalhe_anuncio 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 ml_detalhe_anuncio. 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.
ml_detalhe_anuncio is provided by the Mcp Brazil Marketplaces MCP server (rodrigopg/mcp-brazil-marketplaces). 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 →