Probe a remote MCP endpoint before adding it. If the result requires OAuth, run the core OAuth handoff (
AI agents invoke probeEndpoint to trigger actions in Executor. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Probing remote endpoints and initiating OAuth flows are Execute operations—they trigger external interactions whose outcomes depend on supplied arguments. While not destructive or financial, the ability to probe endpoints and start authentication flows with arbitrary remote systems poses a high blast radius if misused by an agent (could probe internal systems, trigger unintended OAuth flows, or be used for…
From the tool's definition Tool performs network probing of remote MCP endpoints and can initiate OAuth handoff procedures. Description indicates it 'probe[s] a remote MCP endpoint' and can 'run the core OAuth handoff', which are external operations with side effects dependent on the…
Documented attack patterns abuse exactly the kind of access probeEndpoint 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 probeEndpoint:
{
"version": "1",
"default": "deny",
"tools": {
"probeEndpoint": {
"limits": [
{
"counter": "probeendpoint_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}probeEndpoint stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Probe a remote MCP endpoint before adding it. If the result requires OAuth, run the core OAuth handoff (. It is categorised as a Execute tool in the Executor MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Executor MCP server in PolicyLayer and add a rule for probeEndpoint: 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.
probeEndpoint is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the probeEndpoint 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 probeEndpoint. 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.
probeEndpoint 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.