Skip to main content
Glama
Sign In

Pullwire

by dev.pullwire
OverviewDiscussionsAdmin

Website Contact Scraper

website-contacts
Read-only

Get email addresses, phone numbers and Facebook, Instagram, LinkedIn, X, YouTube, TikTok and Pinterest profiles from a list of company websites: homepage plus contact and imprint pages. No login, no browser. Costs 1 credit per result; failed items are free.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "websites": "<websites>"
    },
    "name": "website-contacts"
  }
}

Input Schema

NameRequiredDescriptionDefault
websitesYesCompany domains or website URLs, one per line, e.g. "kaercher.com" or "www.example-bakery.de/kontakt". One result per website; duplicates are skipped.
maxResultsNoStop after this many websites. Empty: all of them.
maxPagesPerWebsiteNoHomepage plus up to this many minus one contact, imprint or about pages. Extra pages are only visited while an email or a phone number is still missing.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, openWorldHint, and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful behavior beyond them: the cost model (1 credit per result, failures free) and the fact that no login/browser session is used. It says nothing about pagination, throttling, or what happens on partial matches, leaving real gaps for a scraper.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences, front-loaded with the output capabilities and followed by the cost/failure caveat. Every clause carries information; nothing is redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a three-parameter, no-output-schema tool, the description covers what is returned (emails, phones, social profiles), the crawl scope, and the billing behavior. It could say more about result shape or failure reporting, but an agent has enough to invoke it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all three parameters are already documented in detail, including the maxPagesPerWebsite default and its 'only while email/phone missing' rule. The description only broadly echoes the homepage-plus-contact/imprint crawl behavior, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (get) and concrete resources (email addresses, phone numbers, and eight named social profile types) extracted from a list of company websites. The scope 'homepage plus contact and imprint pages' makes it unmistakable versus siblings like serp, scrape, or linkedin-company.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear operating context: input is a list of company websites, no login or browser needed, and 1 credit per result with failed items free. It does not state when to prefer a sibling tool (e.g. linkedin-company for firmographic data) or any exclusion, so it stops short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Pullwire toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources