MCP YouTube Transcript
An MCP server retrieving transcripts of YouTube videos
Description from the maker (original English)
53 local SEO data tools: rankings, reviews, audits, keywords, AI visibility.
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.
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": {
"localseodata": {
"command": "npx",
"args": [
"-y",
"@localseodata/mcp-server"
]
}
}
}Run this in your terminal
claude mcp add localseodata -- npx -y @localseodata/mcp-serverPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"localseodata": {
"command": "npx",
"args": [
"-y",
"@localseodata/mcp-server"
]
}
}
}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": {
"localseodata": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@localseodata/mcp-server"
]
}
}
}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.
These 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 localseodata, 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.
The registry does not list a required key, though some servers ask you to sign in on first use.
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 (1.1.0) reached the registry 22 days 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.
Model Context Protocol server for Local SEO Data. It gives AI assistants 53 local SEO data tools: SERP and map rankings, reviews, audits, keyword research, competitor analysis, geogrid tracking, and AI visibility scoring.
Connect once, then ask questions in plain English. Your assistant picks the right tools.
https://mcp.localseodata.com/mcp (streamable HTTP)Add https://mcp.localseodata.com/mcp as a connector in your client and click Connect. You'll be asked to sign in to Local SEO Data (or create an account) and approve access. You don't need to copy an API key.
Local SEO Data) and the URL https://mcp.localseodata.com/mcp.claude mcp add localseodata --transport http https://mcp.localseodata.com/mcp --scope user
Then run /mcp in Claude Code, select localseodata, and choose Authenticate.
Add a custom connector or remote MCP server with the URL https://mcp.localseodata.com/mcp and click Connect. Any client that supports MCP authorization will start the sign-in flow on its own.
If your client can't do OAuth, pass an API key in the URL instead:
sk_live_.https://mcp.localseodata.com/mcp?key=YOUR_API_KEY as the server URL.Example configs:
Cursor (.cursor/mcp.json or ~/.cursor/mcp.json)
{
"mcpServers": { "localseodata": { "url": "https://mcp.localseodata.com/mcp?key=YOUR_API_KEY" } } }
VS Code (GitHub Copilot) (.vscode/mcp.json)
{
"servers": { "localseodata": { "type": "http", "url": "https://mcp.localseodata.com/mcp?key=YOUR_API_KEY" } } }
Windsurf (~/.codeium/windsurf/mcp_config.json)
{
"mcpServers": { "localseodata": { "serverUrl": "https://mcp.localseodata.com/mcp?key=YOUR_API_KEY" } } }
Cline: Settings → MCP Servers → Add Remote Server, with the URL https://mcp.localseodata.com/mcp?key=YOUR_API_KEY.
You can create or revoke keys at any time in the API Keys dashboard. Treat a URL that contains your key like a password.
53 tools in total:
| Category | Tools |
|---|---|
| SERP data | local_pack, organic_serp, maps, local_finder, local_services_ads, ai_overview, ai_mode |
| Other platforms | apple_maps, apple_business_profile, bing_local, bing_business_profile |
| AI visibility | ai_mentions, ai_visibility, ai_compare, ai_top_sources, ai_top_pages, ai_keyword_data, ai_llm_response, ai_scraper, ai_sample, ai_sample_status, ai_match |
| Business data | business_profile, profile_health, qa, business_listings, google_reviews, review_velocity, multi_platform_reviews |
| Keyword research | search_volume, keyword_overview, keyword_suggestions, related_keywords, keywords_for_site, keyword_trends |
| Audits | local_audit, citation_audit, reputation_audit, page_audit |
| Competitive intel | competitor_ads, brand_mentions, backlink_summary, backlink_gap |
| Reports | competitor_gap, local_authority, keyword_opportunities |
| Geogrid | geogrid_scan, geogrid_status |
| Locations | location_search |
| Account / utility | get_balance, history_search, history_get, ping |
AI visibility tools report on ChatGPT, Gemini, Perplexity, Claude and Google's AI Overviews and AI Mode. Each tool's description lists its credit cost, and the server sends your assistant instructions on which tool fits which question.
MCP calls use credits from your Local SEO Data account, the same as REST API calls. get_balance, location_search, ping, geogrid_status, ai_sample_status, history_search and history_get are free. See localseodata.com/pricing for plans, and check usage in your dashboard.
git clone https://github.com/localseodata/mcp-server.git
cd mcp-server npm ci npm run build npm start
The server listens on port 3003 by default (PORT changes it) and serves MCP at /mcp, with a health check at /health. Clients authenticate with ?key=YOUR_API_KEY or an Authorization: Bearer header. A Dockerfile is included.
Optional environment variables:
| Variable | Default | Purpose |
|---|---|---|
API_BASE_URL | https://api.localseodata.com | Local SEO Data API the tools call |
PORT | 3003 | HTTP port |
OAUTH_ENABLED | false | Advertise OAuth and accept OAuth access tokens |
OAUTH_ISSUER | https://localseodata.com | Authorization server |
MCP_RESOURCE_URL | https://mcp.localseodata.com/mcp | This server's public URL, used in OAuth metadata |
OAuth access tokens are only accepted by the API from the hosted server, so a self-hosted copy should use API keys.
For clients that launch a local process:
npm ci && npm run build
LOCALSEODATA_API_KEY=sk_live_... node dist/stdio.js
npm run dev # Watch mode
npm run typecheck # Type check npm test # Run tests npm run build # Compile to dist/
MIT