Return the deterministic MCP selector e2e probe payload.
AI agents call selector_probe to retrieve information from Mcp Registry Registry without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and returns a pre-determined probe payload, consistent with Read category operations (get, fetch, return). No data is modified, deleted, or executed. The word 'Return' indicates a query/fetch operation. E2E probe payloads are typically static test data used for validation, not operational changes.
From the tool's definition Tool description states 'Return the deterministic MCP selector e2e probe payload' — a retrieval operation that returns a payload for testing/probing purposes with no side effects.
Attacks that exploit this kind of access
Return the deterministic MCP selector e2e probe payload. It is categorised as a Read tool in the Mcp Registry Registry MCP Server, which means it retrieves data without modifying state.
Register the Mcp Registry Registry MCP server in PolicyLayer and add a rule for selector_probe: 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 Registry Registry. Nothing to install.
selector_probe 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 selector_probe 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 selector_probe. 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.
selector_probe is provided by the Mcp Registry Registry MCP server (@mastra/mcp-registry-registry). 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 →