AI agents call get_iniciativa 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 retrieves and displays information about a legislative initiative from Portuguese Parliament open data. There are no side effects, data modifications, or external operations triggered. The blast radius of misuse is minimal—at worst, an agent could retrieve information it shouldn't have access to, but no system state or data is altered.
From the tool's definition Tool name 'get_iniciativa' and description 'Get a legislative initiative with full detail' indicates a retrieval operation.
Attacks that exploit this kind of access
Get a legislative initiative with full detail: authors, events, votes, publications, and committee phases (comissoesFases) with rapporteurs, documents, and hearings. 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_iniciativa: 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_iniciativa 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_iniciativa 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_iniciativa. 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_iniciativa 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 →