AI agents call get_peticao to retrieve information from Openar without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns data about a specific petition from the Portuguese Parliament open data. It performs a read-only lookup operation with no side effects, no code execution, no data modification, and no destructive actions. The minimal blast radius (only exposure of public parliamentary data) and the clear read-only semantics place it squarely in the Read category with low severity.
From the tool's definition Tool name is 'get_peticao' (get petition); description states it retrieves 'a petition with committees, rapporteurs, and documents' — purely informational retrieval with no modification, deletion, or execution capability.
Attacks that exploit this kind of access
Get a petition with committees, rapporteurs, and documents. It is categorised as a Read tool in the Openar MCP Server, which means it retrieves data without modifying state.
Register the Openar MCP server in PolicyLayer and add a rule for get_peticao: 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 Openar. Nothing to install.
get_peticao 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 get_peticao 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 get_peticao. 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.
get_peticao is provided by the Openar MCP server (openar-pt/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 →