Search Scout's public licensed-agent directory. Returns agents sourced from state REC public rosters + MLS-ranked prospect lists. Indexed states are listed in scout.coverage() — call that first if you're unsure whether a state has meaningful data. Every result has a claim_url — unclaimed agents c...
Risk signalsHigh parameter count (11 properties) · Bulk/mass operation — affects multiple targets
Part of the Scout server.
Free to start. No card required.
AI agents invoke scout.find_public_agent to trigger processes or run actions in Scout. Execute operations can have side effects beyond the immediate call -- triggering builds, sending notifications, or starting workflows. Rate limits and argument validation are essential to prevent runaway execution.
scout.find_public_agent can trigger processes with real-world consequences. An uncontrolled agent might start dozens of builds, send mass notifications, or kick off expensive compute jobs. PolicyLayer enforces rate limits and validates arguments to keep execution within safe bounds.
Execute tools trigger processes. Rate-limit and validate arguments to prevent unintended side effects.
{
"version": "1",
"default": "deny",
"tools": {
"scout.find_public_agent": {
"limits": [
{
"counter": "scout.find_public_agent_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}See the full Scout policy for all 18 tools.
These attack patterns abuse exactly the kind of access scout.find_public_agent gives an agent. Each links to the full case and the policy that stops it:
Other execute tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
Search Scout's public licensed-agent directory. Returns agents sourced from state REC public rosters + MLS-ranked prospect lists. Indexed states are listed in scout.coverage() — call that first if you're unsure whether a state has meaningful data. Every result has a claim_url — unclaimed agents can claim to curate their AI profile and start receiving AI-routed leads. Unlike scout.find_agent (which requires a live pin), this returns the full directory regardless of pin freshness. Prefer scout.find_agent when you want agents who are live-available right now; prefer scout.find_public_agent when you want broad discoverability. Pass lat/lng OR address (US street address — we'll forward-geocode via Mapbox) to get distance-ascending results with a distance_miles field on each agent; otherwise results are sorted by flika_score descending.. It is categorised as a Execute tool in the Scout MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Scout MCP server in PolicyLayer and add a rule for scout.find_public_agent: 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 Scout. Nothing to install.
scout.find_public_agent 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 scout.find_public_agent 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 scout.find_public_agent. 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.
scout.find_public_agent is provided by the Scout MCP server (https://scout.realestate/api/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 18 Scout tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.