Contact Details Finder

Find a website's emails, phones and social links

find_contact_details

Read-onlyIdempotent

Finds the contact details a company website publishes. Use it when the user asks how to reach a company, or asks for its email, phone or social accounts. For example: "find the contact email of example.com" or "what is the phone number on https://shop.example/contact?". Pass the site address; it reads 10 pages unless max_pages asks for more, up to 20. It returns the emails, sure phones (tel: links), uncertain phones (page text) and social profile links for 13 networks, found on the start page and the same-site pages it links to. It also returns the pages it read, and for each email domain whether it can receive mail (MX) and has SPF and DMARC. It obeys robots.txt, runs no JavaScript and reads public sites only. Don't use it to look up a private person or to collect addresses for bulk mail.

Input Schema

Name	Required	Description
`url`	Yes	The company website or page to start from, such as https://example.com or example.com
`max_depth`	No	How many links away from the start page to go; 0 reads only the start page; 1 by default
`max_pages`	No	Pages to read at most, the start page included; 10 by default
`check_mail`	No	Check MX, SPF and DMARC for each email domain found (true by default)

Output Schema

Name	Required	Description
`url`	Yes	The start address as read
`as_of`	Yes	ISO 8601 time the data was published by its source or fetched from it. A cached answer keeps the time of its fetch.
`notes`	Yes	Limits of this answer; show them
`domain`	Yes	The site's host without www.
`source`	Yes	Who the data comes from, to cite and to check it against.
`status`	Yes
`contacts`	Yes	Each list sorted, without repeats; social links in one canonical https form
`scraped_urls`	Yes	The pages read, in the order they were read
`email_domains`	Yes
`pages_scraped`	Yes	Pages read and searched for contacts

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 21, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations cover the safety profile (readOnly, idempotent, openWorld, non-destructive), and the description goes well beyond them: crawl budget (10 pages default, up to 20), robots.txt compliance, JavaScript disabled, public-sites-only restriction, MX/SPF/DMARC probing, and the distinction between 'sure' tel: phones and uncertain page-text phones. It also discloses it returns the pages read.

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

Conciseness4/5

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

Purpose, usage triggers and examples are front-loaded, then behavior and constraints. It is longer than strictly necessary (e.g., the MX/SPF/DMARC enumeration could be trimmed), but each sentence carries real selection or invocation value.

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

Completeness5/5

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

For a 4-parameter, open-world read tool with an output schema, the description covers scope, limits, defaults, safety boundaries and return contents. Return-value explanation is technically redundant with the output schema but harmless, and no invocation-relevant detail is missing.

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 the schema already explains url, max_depth, max_pages and check_mail in detail. The description restates the page budget and mail-check behavior, adding little beyond what the schema provides, so the baseline of 3 is appropriate.

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?

The description states a specific verb and resource: it 'finds the contact details a company website publishes,' and immediately enumerates the artifact types (emails, tel: phones, page-text phones, social links for 13 networks). It is unambiguous and cannot be confused with the feedback siblings.

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

Usage Guidelines5/5

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

It gives explicit trigger conditions ('when the user asks how to reach a company, or asks for its email, phone or social accounts'), two concrete example queries, and a negative boundary ('Don't use it to look up a private person or to collect addresses for bulk mail'). Nothing about selection is left to inference.

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

All Contact Details Finder tools Inspect

Try in Browser

Let your AI agent see the webWeb-to-screenshot MCP for Claude, Cursor and Codex. No cookie banners. Free to start.snap-render.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.