Search for ridings by name.
AI agents call search_ridings to retrieve information from Elections Canada MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only operation that searches and returns information about Canadian electoral ridings. It performs no writes, deletions, code execution, or financial transactions. The data returned is public election information. Confidence is high because the description is explicit and unambiguous about the retrieval nature of the operation.
From the tool's definition Tool name 'search_ridings' and description 'Search for ridings by name' indicate a query operation that retrieves election data without modification or side effects.
Attacks that exploit this kind of access
Search for ridings by name. It is categorised as a Read tool in the Elections Canada MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Elections Canada MCP Server MCP server in PolicyLayer and add a rule for search_ridings: 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 Elections Canada MCP Server. Nothing to install.
search_ridings 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 search_ridings 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 search_ridings. 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.
search_ridings is provided by the Elections Canada MCP Server MCP server (threefortythree-canada/elections-canada-mcp-server). 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 →