YouTube Channel Email Finder MCP Server

Find YouTube channel emails

find_youtube_channel_emails

Read-onlyIdempotent

Finds email addresses YouTube channels publish on about pages or linked websites, with each source; accepts channel URLs, @handles, IDs, or search terms with subscriber filters.

Instructions

Find the email addresses YouTube channels publish in plain text on their about page or linked website, with the source of each. Takes channels or a search term with a subscriber range. No login. A channel with no published address is free.

Input Schema

Name	Required	Description
`channels`	No	Channel URLs, @handles, or UC channel IDs, up to 500 a run. Clay users: wrap a column in a one item list.
`search_terms`	No	Optional. Themes to find channels by, such as home espresso. Search results come from YouTube's channel search, up to the maximum per search below.
`check_websites`	No	no (default) or yes. yes reads the home page and one contact or about page on a site the channel links to, obeying robots.txt. It finds more addresses and costs more pages per run.
`max_charge_usd`	No	Optional. The run stops before a charge would pass this amount.
`max_subscribers`	No	Optional. Number as text. YouTube rounds subscriber counts, so this filter is approximate.
`min_subscribers`	No	Optional. Number as text. YouTube rounds subscriber counts, so this filter is approximate.
`videos_to_check`	No	Number as text, 0 to 10. Default 0, which is off. YouTube answered most video page reads with a sign in gate in testing, so this finds little and takes longer. Read only when no address has been found yet.
`check_all_sources`	No	no (default) stops at the first source with an address. yes reads them all, which takes longer.
`max_channels_per_search`	No	Number as text, 1 to 200. Default 20.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.0Nov 9, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already declare read-only, idempotent and open-world behaviour, yet the description still adds real context: results carry source attribution, no login is needed, a channel with no published address costs nothing, and website checks obey robots.txt. It does not cover rate limits or output shape, keeping it short of a 5.

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?

Four short sentences, all front-loaded: what is found first, then inputs, then constraints, then the cost edge case. No sentence is filler.

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 nine-parameter, no-output-schema tool the description covers purpose, inputs, auth, safety-relevant site access (robots.txt) and one pricing edge case. Return shape is only loosely implied ('with the source of each'), which is the one clear gap.

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 each of the nine parameters is already documented in detail, including defaults and caveats. The description reinforces the channel/search-term/subscriber-range grouping but adds no syntax or behavioural detail beyond the schema, 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 and resource — finding email addresses that channels publish in plain text on their about page or linked website — and adds scope (plain-text only, with attribution of each source). An agent knows exactly what it gets back without opening the schema.

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?

Explains the two entry modes (explicit channels or a search term with a subscriber range) and the no-login requirement, which frames when the tool applies. It stops short of explicit exclusions or alternatives, but there are no sibling tools to route against, so the gap is minor.

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

Deploy Server

Other Tools

find_youtube_channel_emailsA