capture_lead
Lead-gen/CRM: save a website lead to YOUR private pipeline (needs your registered handle + secret). At least one of name/email/phone. Returns {ok, lead_id}.
This record as markdown: /tools/com-wingmanprotocol-agent-gateway/capture-lead.md
What capture_lead does on Gateway
AI agents use capture_lead to create or update resources in Gateway, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Gateway environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
name | string | — | |
email | string | — | |
notes | string | — | free-text context (drives intent scoring) |
phone | string | — | |
handle | string | Yes | your registered handle (owner-gated) |
secret | string | — | your agent secret |
status | string | — | new|contacted|qualified (default new) |
session_id | string | — | your site session id, optional |
Parameters from the server's own tool schema.
Why capture_lead is rated Medium
This tool creates or modifies data (CRM lead records) in a reversible manner—leads can be updated or deleted. It requires authentication (registered handle + secret) to prevent unauthorized access. The blast radius is moderate: misuse could result in spam/junk data polluting a CRM pipeline or unauthorized lead capture, but does not involve data destruction, code execution, or financial transactions.
From the tool's definition Tool description explicitly states 'save a website lead to YOUR private pipeline', indicating creation of new records in a CRM system. Returns {ok, lead_id} confirming successful write operation.
Risk signalsHandles credentials or secrets (secret)
Attacks that exploit this kind of access
The rule that runs capture_lead 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 capture_lead, this is the rule to start with:
capture_lead stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. 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 capture_lead call is checked against it from then on.
Questions about capture_lead
Lead-gen/CRM: save a website lead to YOUR private pipeline (needs your registered handle + secret). At least one of name/email/phone. Returns {ok, lead_id}. It is categorised as a Write tool in the Gateway MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
capture_lead accepts 8 parameters: name, email, notes, phone, handle, secret, status, session_id. Required: handle. 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 capture_lead: 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.
capture_lead 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 capture_lead 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 capture_lead. 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.
capture_lead 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