Runs a new ranking scan for a business. COSTS CREDITS — always confirm with the user before running. Requires: Place ID (business must be saved first), keyword, center coordinates (lat/lng), grid size, radius, measurement unit, and platform. Available platforms: google (Maps), apple (Apple Maps),...
AI agents invoke runLocalFalconScan to trigger actions in Local Falcon MCP Server. 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.
While the tool retrieves SEO data like other sibling tools, runLocalFalconScan is distinct because it EXECUTES an operation that consumes paid credits and produces time-dependent side effects. This is not a passive read (like getLocalFalconCompetitorReport) but an active scan trigger. The resource cost and external operation initiation place it in Execute rather than Read.
From the tool's definition Tool description explicitly states 'COSTS CREDITS' and 'Runs a new ranking scan' with specific parameters (Place ID, keyword, coordinates, grid size, radius, platform).
Documented attack patterns abuse exactly the kind of access runLocalFalconScan gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Local Falcon MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for runLocalFalconScan:
{
"version": "1",
"default": "deny",
"tools": {
"runLocalFalconScan": {
"limits": [
{
"counter": "runlocalfalconscan_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} runLocalFalconScan 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.
Runs a new ranking scan for a business. COSTS CREDITS — always confirm with the user before running. Requires: Place ID (business must be saved first), keyword, center coordinates (lat/lng), grid size, radius, measurement unit, and platform. Available platforms: google (Maps), apple (Apple Maps), gaio (Google AI Overviews), chatgpt (ChatGPT), gemini (Gemini), grok (Grok), aimode (Google AI Mode). Enable aiAnalysis for AI-generated insights on the results (Google Maps only). Grid size and radius should match the business type and service area. IMPORTANT: Scans take 30 seconds to several minutes to complete depending on grid size and queue load. If the response says. It is categorised as a Execute tool in the Local Falcon MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Local Falcon MCP Server MCP server in PolicyLayer and add a rule for runLocalFalconScan: 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 Local Falcon MCP Server. Nothing to install.
runLocalFalconScan 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 runLocalFalconScan 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 runLocalFalconScan. 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.
runLocalFalconScan is provided by the Local Falcon MCP Server MCP server (local-falcon/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Local Falcon MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
37 Local Falcon MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.