How do I install Pulse?

Pulse is a local plugin. Install it using npm package: pulse-mcp and add the generated configuration snippet to your AI app's MCP config file. Then restart your AI app.

Is Pulse safe to use?

Yes. Pulse passed MCP Marketplace's automated security scan with a score of 10/10 (low risk). Every server on MCP Marketplace is security-scanned before it's listed; see the full security report on this page for the findings and permissions.

What AI apps work with Pulse?

Pulse uses the Model Context Protocol (MCP) and works with any MCP-compatible AI app, including Claude, ChatGPT / Codex, Gemini, Copilot, Cursor, and more.

Back to Browse

Pulse MCP Server

by Patwalls

Developer ToolsLow Risk10.0MCP RegistryLocal

Free

Server data from the Official MCP Registry

Free, agent-first social-post metrics — a post URL in, views/likes/comments out.

About

Free, agent-first social-post metrics — a post URL in, views/likes/comments out.

Security Report

10.0

Low Risk10.0Low Risk

Valid MCP server (2 strong, 4 medium validity signals). No known CVEs in dependencies. Package registry verified. Imported from the Official MCP Registry.

3 files analyzed · 1 issue found

Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.

Permissions Required

This plugin requests these system permissions. Most are normal for its category.

HTTP Network Access

Connects to external APIs or services over the internet.

env_vars

Check that this permission is expected for this type of plugin.

How to Install

Add this to your MCP configuration file:

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

Documentation

View on GitHub

From the project's GitHub 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 five new tools.

Tools

Tool	Input	Output
`metrics`	one post URL (short links like `vm.tiktok.com`/`t.co` OK)	`{ platform, views, likes, comments, shares, quotes, bookmarks, publishedAt, title, author, thumbnail }`
`metrics_batch`	many URLs (mixed post + profile URLs welcome)	the same, one per URL (partial failures don't fail the batch)
`history`	one post or profile URL (+ optional `since` for the delta)	the recorded growth curve — `{ count, points }` (posts: `{ t, views, likes, comments }`, profiles: `{ t, followers, posts }`), a snapshot per fresh fetch
`profile`	one profile URL	account-level metrics — `{ handle, name, followers, following, posts, verified, avatar }` (YouTube, TikTok, Instagram, X, Bluesky, Mastodon)
`profile_batch`	many profile URLs (max 50)	same as `profile`, one per URL — order preserved; partial failures don't fail the batch. Compare follower counts across a list of creators.

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	views, likes, comments, shares (retweets), quotes, bookmarks	views via X's own guest API (tweets since ~Dec 2022)
TikTok	views, likes, comments, shares
Bluesky	likes, comments, shares (reposts), quotes	public AppView API; Bluesky has no view counts
Mastodon	likes, boosts, replies	per-instance public REST API (major instances)
Instagram	views, likes, comments	public posts via the guest API
Threads	post metrics need a login	post metrics → `login_required`; profile metrics (followers/verified) work via `/profile`
LinkedIn	— (posts need login)	post metrics → `login_required`; profiles also login-walled

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.

Reviews

No reviews yet

Be the first to review this server!

More Developer Tools MCP Servers

Fetch

Free

by Modelcontextprotocol · Developer Tools

Web content fetching and conversion for efficient LLM usage

Git

Free

by Modelcontextprotocol · Developer Tools

Read, search, and manipulate Git repositories programmatically

Toleno

Free

by Toleno · Developer Tools

Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.

Pulse MCP Server

About

Security Report

Findings (1)

Permissions Required

How to Install

Documentation

pulse-mcp

Tools

Platform coverage

Config

Reviews

No reviews yet

More Developer Tools MCP Servers

Fetch

Git

Toleno

mcp-creator-python

MarkItDown

FinAgent