Website Contact & Social Extractor MCP

Extracts emails, validated phone numbers, WhatsApp links, social profiles, and addresses from a website's public pages. It respects robots.txt, uses no proxies or guessing, and returns schema.org company data from the homepage and contact pages.

Visit Noah's Arch

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Vendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-01Operated by Noah's Arch

You need:Without a key the catalogue and a few free tools work; paid tools answer 402 until a key is setX-API-Key: YOUR_KEY

MCP endpoint (Streamable HTTP)

https://contacts.noahsarch.tech/mcp

Vendor documentation

What you can do with it

Extract contact details from a target website
Validate phone numbers as mobile or landline
Find social media profiles on 18 platforms
Retrieve schema.org company data

Source and maintenance

Vendor evidenceRegistry 0.1.1

mcp-registry: tech.noahsarch/website-contact-extractor@0.1.1 Project website

Protocol and capabilities

Server: website-contact-extractor 0.1.0
MCP protocol: 2025-06-18
Tools: 5 advertised
Resources: 2 advertised
Resource templates: 0 advertised
Prompts: 0 advertised

Server-advertised capabilities

{
  "tools": {
    "listChanged": false
  },
  "prompts": {
    "listChanged": false
  },
  "resources": {
    "subscribe": false,
    "listChanged": false
  }
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

Get a company's contact details from its website. extract_contacts(url) fetches the homepage and its contact/about pages and returns emails, phone numbers (validated, E.164, mobile vs landline), WhatsApp links, social profiles, postal addresses and organisation data from schema.org markup — deduplicated with the page each item came from. find_social_profiles for just the social links; extract_contacts_bulk for up to 50 sites in one call (lead lists); extract_from_html when you already have the page; check_url to see whether a site is reachable and where it redirects. Pass region (e.g. 'AE') so local phone numbers without +country code are read correctly. Items with source=text came from visible text and deserve a second look; mailto/tel/jsonld items are explicit. Only static HTML is read; sites that load contacts with JavaScript return an empty result with a warning. Respects robots.txt. Response: result with emails[] (email, source, role), phones[] (e164, international, region, type, source), whatsapp[], social{platform: [url, handle]}, addresses[], organization{}, pages[] (what was fetched, status) and summary{}, plus data_confidence, estimated_items[], sources[], data_version, warnings[] and a disclaimer. Charged per page actually fetched; failed fetches are free. URLs are not logged.

Tools

5 advertised

extract_contacts — Extract contacts from a website

Advertised by the server during the last successful anonymous check.

Advertised read-only

Fetch a site's homepage and up to max_pages-1 contact/about pages and return every email, phone (validated, E.164, type), WhatsApp link, social profile, postal address and organisation field found, with provenance per item. Example: url 'noahsarch.tech', max_pages 3, region 'AE'. Response: result with emails[] (email, source, role), phones[] (e164, international, region, type, source), whatsapp[], social{platform: [url, handle]}, addresses[], organization{}, pages[] (what was fetched, status) and summary{}, plus data_confidence, estimated_items[], sources[], data_version, warnings[] and a disclaimer. Charged per page actually fetched; failed fetches are free. URLs are not logged.

extract_contacts input schema

{
  "type": "object",
  "title": "extract_contactsArguments",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "title": "Url",
      "description": "Website URL (scheme optional): 'example.com' or 'https://example.com/about'."
    },
    "region": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Region",
      "default": null,
      "description": "ISO 3166-1 alpha-2 country used to interpret phone numbers written without a country code (e.g. 'AE', 'GB', 'US'). Omit if unknown."
    },
    "max_pages": {
      "type": "integer",
      "title": "Max Pages",
      "default": 3,
      "description": "Homepage plus up to (max_pages-1) contact/about pages found on it. 1 = homepage only."
    },
    "include_social": {
      "type": "boolean",
      "title": "Include Social",
      "default": true,
      "description": "Include social-profile links (Facebook, Instagram, X, LinkedIn, YouTube, TikTok, Telegram, Snapchat, Pinterest, Threads, GitHub…)."
    },
    "respect_robots": {
      "type": "boolean",
      "title": "Respect Robots",
      "default": true,
      "description": "Honour the site's robots.txt (default). Set false only for sites you own."
    },
    "follow_contact_pages": {
      "type": "boolean",
      "title": "Follow Contact Pages",
      "default": true,
      "description": "Also fetch the site's contact/about/impressum pages (same site only)."
    }
  }
}

extract_contacts output schema

{
  "type": "object",
  "title": "extract_contactsDictOutput",
  "additionalProperties": true
}

extract_contacts annotations

{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

find_social_profiles — Find a website's social-media profiles

Advertised by the server during the last successful anonymous check.

Advertised read-only

Homepage only: Facebook, Instagram, X/Twitter, LinkedIn, YouTube, TikTok, Telegram, Snapchat, Pinterest, Threads, GitHub, TripAdvisor, Google Business links plus WhatsApp chat links, with handles. Share buttons are excluded. Example: url 'https://example.com'. Response: result with emails[] (email, source, role), phones[] (e164, international, region, type, source), whatsapp[], social{platform: [url, handle]}, addresses[], organization{}, pages[] (what was fetched, status) and summary{}, plus data_confidence, estimated_items[], sources[], data_version, warnings[] and a disclaimer. Charged per page actually fetched; failed fetches are free. URLs are not logged.

find_social_profiles input schema

{
  "type": "object",
  "title": "find_social_profilesArguments",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "title": "Url",
      "description": "Website URL."
    }
  }
}

find_social_profiles output schema

{
  "type": "object",
  "title": "find_social_profilesDictOutput",
  "additionalProperties": true
}

find_social_profiles annotations

{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

extract_contacts_bulk — Extract contacts from up to 50 websites

Advertised by the server during the last successful anonymous check.

Advertised read-only

One call for a lead list: each site gets homepage + contact pages (max_pages), results per site plus a summary (sites with email/phone/WhatsApp, failures). Charged per page fetched across all sites. Example: urls ['a.com','b.ae'], max_pages 2, region 'AE'. Response: result with emails[] (email, source, role), phones[] (e164, international, region, type, source), whatsapp[], social{platform: [url, handle]}, addresses[], organization{}, pages[] (what was fetched, status) and summary{}, plus data_confidence, estimated_items[], sources[], data_version, warnings[] and a disclaimer. Charged per page actually fetched; failed fetches are free. URLs are not logged.

extract_contacts_bulk input schema

{
  "type": "object",
  "title": "extract_contacts_bulkArguments",
  "required": [
    "urls"
  ],
  "properties": {
    "urls": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "title": "Urls",
      "description": "Up to 50 website URLs (one per company). Duplicate sites are merged."
    },
    "region": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Region",
      "default": null,
      "description": "ISO 3166-1 alpha-2 country used to interpret phone numbers written without a country code (e.g. 'AE', 'GB', 'US'). Omit if unknown."
    },
    "max_pages": {
      "type": "integer",
      "title": "Max Pages",
      "default": 2,
      "description": "Pages per site (homepage + contact pages)."
    },
    "include_social": {
      "type": "boolean",
      "title": "Include Social",
      "default": true,
      "description": ""
    }
  }
}

extract_contacts_bulk output schema

{
  "type": "object",
  "title": "extract_contacts_bulkDictOutput",
  "additionalProperties": true
}

extract_contacts_bulk annotations

{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

extract_from_html — Extract contacts from HTML you already have

Advertised by the server during the last successful anonymous check.

Advertised read-only

Same parser, no fetching: emails (incl. obfuscated 'name [at] domain [dot] com'), phones, WhatsApp, social links, addresses, schema.org organisation data, and the contact-page links present. Free. Example: html '<a href="mailto:x@y.com">'. Response: result with emails[] (email, source, role), phones[] (e164, international, region, type, source), whatsapp[], social{platform: [url, handle]}, addresses[], organization{}, pages[] (what was fetched, status) and summary{}, plus data_confidence, estimated_items[], sources[], data_version, warnings[] and a disclaimer. Charged per page actually fetched; failed fetches are free. URLs are not logged.

extract_from_html input schema

{
  "type": "object",
  "title": "extract_from_htmlArguments",
  "required": [
    "html"
  ],
  "properties": {
    "html": {
      "type": "string",
      "title": "Html",
      "description": "HTML (or plain text) you already have."
    },
    "region": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Region",
      "default": null,
      "description": "ISO 3166-1 alpha-2 country used to interpret phone numbers written without a country code (e.g. 'AE', 'GB', 'US'). Omit if unknown."
    },
    "base_url": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Base Url",
      "default": null,
      "description": "Page URL, used to resolve relative links and decide which links are same-site."
    }
  }
}

extract_from_html output schema

{
  "type": "object",
  "title": "extract_from_htmlDictOutput",
  "additionalProperties": true
}

extract_from_html annotations

{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

check_url — Check that a website is reachable

Advertised by the server during the last successful anonymous check.

Advertised read-only

GET the URL (robots-respecting, public hosts only) and report status, final URL after redirects, content type, title, declared languages and whether a contact page is linked. Use before a bulk job or to clean a URL list. Example: url 'example.com'. Response: result with emails[] (email, source, role), phones[] (e164, international, region, type, source), whatsapp[], social{platform: [url, handle]}, addresses[], organization{}, pages[] (what was fetched, status) and summary{}, plus data_confidence, estimated_items[], sources[], data_version, warnings[] and a disclaimer. Charged per page actually fetched; failed fetches are free. URLs are not logged.

check_url input schema

{
  "type": "object",
  "title": "check_urlArguments",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "title": "Url",
      "description": ""
    },
    "respect_robots": {
      "type": "boolean",
      "title": "Respect Robots",
      "default": true,
      "description": ""
    }
  }
}

check_url output schema

{
  "type": "object",
  "title": "check_urlDictOutput",
  "additionalProperties": true
}

check_url annotations

{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

Prompts

0 advertised

No prompt definitions available.

Resources

2 advertised

data_version — Data version

Advertised by the server during the last successful anonymous check.

Current data/rules version.

data_version URI

website-contact-extractor://data-version

MIME type: text/plain

metrics — Aggregate metrics

Advertised by the server during the last successful anonymous check.

Aggregate counters only (tool, status, latency bucket). No queries are logged.

metrics URI

website-contact-extractor://metrics

MIME type: text/plain

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks: 1 of 1 (100%)
Average latency: 2529 ms
95th percentile latency: 2529 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

Nov 1, 2026, 9:23 AM UTC · probe · passed · 2529 ms · metadata changed · 5 tool(s), 2 resource(s), 0 resource template(s), 0 prompt(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.

Claude Code configuration

claude mcp add --transport http website-contact-social-extractor-mcp https://contacts.noahsarch.tech/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).

Codex configuration

codex mcp add website-contact-social-extractor-mcp --url https://contacts.noahsarch.tech/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable website-contact-social-extractor-mcp in your MCP settings.

Cursor configuration

{
  "mcpServers": {
    "website-contact-social-extractor-mcp": {
      "url": "https://contacts.noahsarch.tech/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).

Cline configuration

{
  "mcpServers": {
    "website-contact-social-extractor-mcp": {
      "type": "streamableHttp",
      "url": "https://contacts.noahsarch.tech/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start website-contact-social-extractor-mcp and inspect its tools.

VS Code configuration

{
  "servers": {
    "website-contact-social-extractor-mcp": {
      "type": "http",
      "url": "https://contacts.noahsarch.tech/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.

Gemini CLI configuration

gemini mcp add --transport http website-contact-social-extractor-mcp https://contacts.noahsarch.tech/mcp

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.

Claude Desktop configuration

{
  "mcpServers": {
    "website-contact-social-extractor-mcp": {
      "url": "https://contacts.noahsarch.tech/mcp"
    }
  }
}

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.

Windsurf configuration

{
  "mcpServers": {
    "website-contact-social-extractor-mcp": {
      "serverUrl": "https://contacts.noahsarch.tech/mcp"
    }
  }
}

Let your agent find its tools

Find servers like Website Contact & Social Extractor MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows

See all 4,473

Do you run Website Contact & Social Extractor MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing

Website Contact & Social Extractor MCP

Endpoint and access

What you can do with it

Source and maintenance

Protocol and capabilities

Server-provided instructions

Tools

Prompts

Resources

30-day availability

Maintenance history

Connect from your client

Claude Code

Codex

Cursor

Cline

VS Code

Gemini CLI

Claude Desktop

Windsurf

Let your agent find its tools

Other productivity and knowledge servers

Do you run Website Contact & Social Extractor MCP?