lookup_faq
Lead-gen/CRM: fuzzy-match a visitor question against a FAQ list you pass in (difflib, literal not semantic). Public. Returns {ok, matched, confidence, answer}.
This record as markdown: /tools/com-wingmanprotocol-agent-gateway/lookup-faq.md
What lookup_faq does on Gateway
AI agents call lookup_faq to retrieve information from Gateway without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
faqs | array | Yes | [{q, a}, ...] your FAQ entries |
question | string | Yes | the visitor's question |
threshold | number | — | min match ratio 0-1 (default 0.4) |
Parameters from the server's own tool schema.
Why lookup_faq is rated Low
This is a read-only operation that retrieves FAQ data based on search criteria. No side effects, no data creation, modification, or deletion. The tool is passive and informational. Low severity because even if misused by an agent, it only returns information from a FAQ database—no financial, destructive, or execution risks.
From the tool's definition Tool performs fuzzy-matching lookup against a provided FAQ list and returns results (ok, matched, confidence, answer). No modifications, deletions, or external operations are triggered.
Attacks that exploit this kind of access
The rule that runs lookup_faq safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Gateway, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For lookup_faq, this is the rule to start with:
lookup_faq is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Gateway, apply this rule, and every lookup_faq call is checked against it from then on.
Questions about lookup_faq
Lead-gen/CRM: fuzzy-match a visitor question against a FAQ list you pass in (difflib, literal not semantic). Public. Returns {ok, matched, confidence, answer}. It is categorised as a Read tool in the Gateway MCP Server, which means it retrieves data without modifying state.
lookup_faq accepts 3 parameters: faqs, question, threshold. Required: faqs, question. The full parameter table on this page comes from the server's own tool schema.
Register the Gateway MCP server in PolicyLayer and add a rule for lookup_faq: 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 Gateway. Nothing to install.
lookup_faq 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 lookup_faq 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 lookup_faq. 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.
lookup_faq is provided by the Gateway MCP server (https://wingmanprotocol.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Gateway, and thousands of servers like it.
This server
Across the catalogue