get_endpoint_schema
AI agents call get_endpoint_schema to retrieve information from Mcp Camara without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to retrieve endpoint schema information from the Brazilian Chamber of Deputies API, which is a read-only operation. The context of an open data API and the absence of any mutation or execution semantics support classification as Read.
From the tool's definition Tool name 'get_endpoint_schema' suggests retrieval of schema metadata. No description provided, but naming pattern aligns with sibling tools that are query/retrieval operations (get_bills_by_deputy, get_deputy_by_name, get_deputy_expenses, list_endpoints).
Attacks that exploit this kind of access
get_endpoint_schema. It is categorised as a Read tool in the Mcp Camara MCP Server, which means it retrieves data without modifying state.
Register the Mcp Camara MCP server in PolicyLayer and add a rule for get_endpoint_schema: 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 Camara. Nothing to install.
get_endpoint_schema 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_endpoint_schema 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_endpoint_schema. 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_endpoint_schema is provided by the Mcp Camara MCP server (vrtornisiello/mcp-camara). 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 →