pulse-mcp

pulse-mcp

Free MCP server for fetching social media metrics (views, likes, comments) from public post URLs across YouTube, Twitter, TikTok, and Instagram. No API key needed.

Category
Visit Server

README

pulse-mcp

MCP server for Pulse — a free, agent-first social-post metrics API. Give any MCP client (Claude Desktop, Cursor, …) the numbers behind any public post: hand it a URL, get back views, likes, comments, and the publish date as clean JSON. No signup, no API key.

{ "mcpServers": { "pulse": { "command": "npx", "args": ["-y", "pulse-mcp"] } } }

That's it — drop it in your MCP config and your agent has four new tools.

Tools

Tool Input Output
metrics one post URL (short links like vm.tiktok.com/t.co OK) { platform, views, likes, comments, publishedAt, title, author, thumbnail }
metrics_batch many URLs the same, one per URL (partial failures don't fail the batch)
history one post URL the recorded growth curve — { count, points: [{ t, views, likes, comments }] }, a snapshot per fresh fetch
profile one profile URL account-level metrics — { handle, name, followers, following, posts, verified, avatar } (YouTube, TikTok, Instagram, X)

Example — ask your agent "how did this video do?" with a link, and it gets:

{
  "platform": "youtube",
  "views": 1781088936,
  "likes": 19147197,
  "comments": null,
  "publishedAt": "2009-10-25T06:57:33.000Z",
  "title": "Rick Astley - Never Gonna Give You Up (Official Video)"
}

Platform coverage

Platform Returns Notes
YouTube views, likes
X / Twitter likes, comments views aren't public
TikTok views, likes, comments
Instagram views, likes, comments public posts via the guest API
Threads, LinkedIn need a logged-in session; returns a clear login_required (never fake zeros)

It reads each platform's own public pages from a residential IP, so it sees what a browser sees — and it's honest about the edges: a deleted/private post comes back content_unavailable, a login-walled one login_required, never a silent row of zeros.

Config

  • Free — no account, no key, no wallet.
  • PULSE_API_URL — override the backend (defaults to https://pulse.walls.sh).

Built in public as Wall #002 of walls.sh. Docs: https://pulse.walls.sh/docs · machine-readable: /llms.txt · OpenAPI.

MIT.

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured