Discover OAuth authorization-server metadata from an issuer or protected-resource URL so client registration can be pre-filled.
AI agents call oauth.probe to retrieve information from Executor without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries OAuth server metadata endpoints to retrieve configuration data (authorization endpoints, token endpoints, supported scopes, etc.). This is a read-only discovery operation against standard OAuth metadata endpoints that are designed to be publicly accessible. It does not modify, delete, or execute arbitrary code; it simply retrieves configuration information to populate registration forms.
From the tool's definition Tool name 'oauth.probe' and description 'Discover OAuth authorization-server metadata from an issuer or protected-resource URL' indicate retrieval of publicly available OAuth server configuration information with no side effects.
Documented attack patterns abuse exactly the kind of access oauth.probe gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Executor, and nothing reaches the server without passing your rules. This is the rule we recommend for oauth.probe:
{
"version": "1",
"default": "deny",
"tools": {
"oauth.probe": {}
}
}oauth.probe is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Discover OAuth authorization-server metadata from an issuer or protected-resource URL so client registration can be pre-filled. It is categorised as a Read tool in the Executor MCP Server, which means it retrieves data without modifying state.
Register the Executor MCP server in PolicyLayer and add a rule for oauth.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 Executor. Nothing to install.
oauth.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 oauth.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 oauth.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.
oauth.probe is provided by the Executor MCP server (rhyssullivan/executor). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 29 Executor tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
29 Executor tools catalogued and risk-classified — across an index of 42,500+ MCP servers.