MCP YouTube Transcript
An MCP server retrieving transcripts of YouTube videos
Description from the maker (original English)
Outreach sales engagement MCP server: prospects, sequences, accounts, tasks, and mailings
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
OUTREACH_CLIENT_ID, OUTREACH_CLIENT_SECRET, OUTREACH_ACCESS_TOKEN, OUTREACH_CONFIG_DIR, OUTREACH_OAUTH_PORT, OUTREACH_OAUTH_SCOPESValues marked secret are keys to your account. Never share them or paste them into a chat.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"outreach": {
"command": "npx",
"args": [
"-y",
"@mindstone/mcp-server-outreach"
],
"env": {
"OUTREACH_CLIENT_ID": "your-value",
"OUTREACH_CLIENT_SECRET": "your-value",
"OUTREACH_ACCESS_TOKEN": "your-value",
"OUTREACH_CONFIG_DIR": "your-value",
"OUTREACH_OAUTH_PORT": "your-value",
"OUTREACH_OAUTH_SCOPES": "your-value"
}
}
}
}Run this in your terminal
claude mcp add outreach --env OUTREACH_CLIENT_ID=your-value --env OUTREACH_CLIENT_SECRET=your-value --env OUTREACH_ACCESS_TOKEN=your-value --env OUTREACH_CONFIG_DIR=your-value --env OUTREACH_OAUTH_PORT=your-value --env OUTREACH_OAUTH_SCOPES=your-value -- npx -y @mindstone/mcp-server-outreachFill in the empty values before running it.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"outreach": {
"command": "npx",
"args": [
"-y",
"@mindstone/mcp-server-outreach"
],
"env": {
"OUTREACH_CLIENT_ID": "your-value",
"OUTREACH_CLIENT_SECRET": "your-value",
"OUTREACH_ACCESS_TOKEN": "your-value",
"OUTREACH_CONFIG_DIR": "your-value",
"OUTREACH_OAUTH_PORT": "your-value",
"OUTREACH_OAUTH_SCOPES": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"outreach": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@mindstone/mcp-server-outreach"
],
"env": {
"OUTREACH_CLIENT_ID": "your-value",
"OUTREACH_CLIENT_SECRET": "your-value",
"OUTREACH_ACCESS_TOKEN": "your-value",
"OUTREACH_CONFIG_DIR": "your-value",
"OUTREACH_OAUTH_PORT": "your-value",
"OUTREACH_OAUTH_SCOPES": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
OUTREACH_CONFIG_DIR envOUTREACH_OAUTH_PORT envOUTREACH_OAUTH_SCOPES envThese settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026
The registry name was verified with the GitHub account mindstone, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
You need to fill in: OUTREACH_CLIENT_ID, OUTREACH_CLIENT_SECRET, OUTREACH_ACCESS_TOKEN
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (0.2.1) reached the registry 3 months ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.
In the same category: MCP YouTube Transcript, Google Analytics MCP, BibiGPT YouTube Video Summarizer
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
An MCP server retrieving transcripts of YouTube videos
GA4 MCP server for AI agents: schema discovery, server-side aggregation, analysis-ready defaults.
AI video summarizer: summarize and transcribe YouTube, Bilibili, TikTok and podcast videos.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
Outreach sales engagement MCP server — prospects, sequences, accounts, tasks, and mailings via Outreach API.
After clicking the button, your host will prompt you to fill: OUTREACH_CLIENT_ID, OUTREACH_CLIENT_SECRET, OUTREACH_ACCESS_TOKEN, OUTREACH_CONFIG_DIR, OUTREACH_OAUTH_PORT.
Manual config for Claude Desktop / Claude Code / Goose / Continue.dev (Outreach)
{
"mcpServers": { "Outreach": { "command": "npx", "args": [ "-y", "@mindstone/mcp-server-outreach" ], "env": { "OUTREACH_CLIENT_ID": "", "OUTREACH_CLIENT_SECRET": "", "OUTREACH_ACCESS_TOKEN": "", "OUTREACH_CONFIG_DIR": "~/.mcp/outreach", "OUTREACH_OAUTH_PORT": "0" } } } }
OUTREACH_CLIENT_SECRET)STATUS.jsonnpx -y @mindstone/mcp-server-outreach
Set these environment variables to use standalone OAuth authentication:
OUTREACH_CLIENT_ID=your_client_id
OUTREACH_CLIENT_SECRET=your_client_secret
Then call the outreach_connect_account tool to initiate the OAuth flow.
If you have a static access token:
OUTREACH_ACCESS_TOKEN=your_access_token
OUTREACH_CONFIG_DIR=~/.mcp/outreach # Custom config directory (default: ~/.mcp/outreach)
OUTREACH_OAUTH_PORT=0 # OAuth callback port (default: OS-assigned) OUTREACH_OAUTH_SCOPES="prospects.all sequences.all sequenceStates.all sequenceSteps.read sequenceTemplates.read templates.read accounts.all users.read tasks.all mailings.read calls.read mailboxes.read"
The OUTREACH_OAUTH_SCOPES value above is the built-in default, which covers every tool the connector ships. If you connected an account before these scopes were added (or you override the variable), re-run outreach_connect_account so the new token picks them up.
custom_fields mapped to custom1..custom35)custom_fields)mailbox_id on enrollment)The connector supports four authentication modes, detected once at startup:
| Mode | Detection | Description |
|---|---|---|
bridge | MCP_HOST_BRIDGE_STATE set | Host app manages OAuth |
standalone_oauth | OUTREACH_CLIENT_ID + OUTREACH_CLIENT_SECRET set | Local OAuth with browser redirect |
manual_token | OUTREACH_ACCESS_TOKEN set | Static access token |
unconfigured | No auth env vars | Tools return setup guidance |
Precedence: bridge > standalone_oauth > manual_token > unconfigured
id, prospect_id, sequence_id, account_id, mailbox_id, user_id, owner_id) accepts digits only (/^\d+$/). Non-numeric values are rejected with VALIDATION_ERROR before any API request is made — Outreach IDs are always numeric, so anything else indicates a bad value rather than a real lookup.AMBIGUOUS_STATE (no record is modified); if every state is finished it returns NOT_FOUND.All user-authored text returned by the Outreach API (names, emails, mailing subjects, template bodies, task notes, tags, custom fields) is wrapped in envelopes so MCP hosts and models treat third-party CRM content as data, not instructions. Vendor-generated structure (IDs, timestamps, lifecycle states) is returned raw. Vendor error text (API error details, non-JSON error bodies, and OAuth token-exchange failures) is truncated to 500 characters and enveloped the same way (source="outreach:api-error") before it appears in error messages.
FSL-1.1-MIT