Route a customer request to local businesses — food orders, delivery, services, or any job. Use this to place an order at a restaurant, request a delivery, get quotes for services, or connect a customer agent to a business. Supports delivery (first-to-accept) and proposal (collect quotes) modes. ...
Risk signalsHigh parameter count (10 properties)
Part of the Local Intel server.
Free to start. No card required.
AI agents use local_intel_rfq to create or modify resources in Local Intel. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.
Without a policy, an AI agent could call local_intel_rfq repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Local Intel.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
{
"version": "1",
"default": "deny",
"tools": {
"local_intel_rfq": {
"limits": [
{
"counter": "local_intel_rfq_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}See the full Local Intel policy for all 27 tools.
These attack patterns abuse exactly the kind of access local_intel_rfq gives an agent. Each links to the full case and the policy that stops it:
Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
Route a customer request to local businesses — food orders, delivery, services, or any job. Use this to place an order at a restaurant, request a delivery, get quotes for services, or connect a customer agent to a business. Supports delivery (first-to-accept) and proposal (collect quotes) modes. Set autonomy=full for fully autonomous agent flow (no human needed), approve for agent-picks/human-confirms, human for manual selection. Returns rfq_id to poll with local_intel_rfq_status. Examples: order food from a restaurant, book a contractor, request a driver.. It is categorised as a Write tool in the Local Intel MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Local Intel MCP server in PolicyLayer and add a rule for local_intel_rfq: 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 Intel. Nothing to install.
local_intel_rfq is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the local_intel_rfq 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 local_intel_rfq. 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.
local_intel_rfq is provided by the Local Intel MCP server (https://gsb-swarm-production.up.railway.app/api/local-intel/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 27 Local Intel 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.