extract_contacts
Extract email addresses, social media links, and phone numbers from any URL. Use this for lead generation, finding contact information on company websites, or researching business contacts. Returns emails, social links (LinkedIn, Twitter, GitHub, etc.), and phone numbers found in the page content...
This record as markdown: /tools/com-gadgethumans-swarm-x402-middleware/extract-contacts.md
What extract_contacts does on X402 Middleware
AI agents call extract_contacts to retrieve information from X402 Middleware 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 |
|---|---|---|---|
url | string | Yes |
Parameters from the server's own tool schema.
Why extract_contacts is rated Low
This is a read-only data extraction tool. It retrieves publicly available contact information from web pages without modifying, executing code, or performing financial transactions. Severity is medium rather than low because collecting contact information at scale could enable spam, phishing, or social engineering attacks if misused by an AI agent, though the tool itself performs no harmful actions.
From the tool's definition Tool explicitly extracts contact information from URLs with no modification or deletion capability. Description states it 'extracts email addresses, social media links, and phone numbers' and 'returns' this information. Single parameter is a URL to scan.
Risk signalsAccepts URL/endpoint input (url)
Attacks that exploit this kind of access
The rule that runs extract_contacts safely
PolicyLayer is an MCP gateway: it sits between your AI agents and X402 Middleware, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For extract_contacts, this is the rule to start with:
extract_contacts 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 X402 Middleware, apply this rule, and every extract_contacts call is checked against it from then on.
Questions about extract_contacts
Extract email addresses, social media links, and phone numbers from any URL. Use this for lead generation, finding contact information on company websites, or researching business contacts. Returns emails, social links (LinkedIn, Twitter, GitHub, etc.), and phone numbers found in the page content. Parameters: url — The full URL to scan for contacts (e.g. "https://example.com/contact"). It is categorised as a Read tool in the X402 Middleware MCP Server, which means it retrieves data without modifying state.
extract_contacts accepts 1 parameter: url. Required: url. The full parameter table on this page comes from the server's own tool schema.
Register the X402 Middleware MCP server in PolicyLayer and add a rule for extract_contacts: 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 X402 Middleware. Nothing to install.
extract_contacts 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 extract_contacts 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 extract_contacts. 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.
extract_contacts is provided by the X402 Middleware MCP server (@gadgethumans/x402). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on X402 Middleware, and thousands of servers like it.
This server
Across the catalogue