Puppeteer MCP

Created By
iatsiuk6 months ago
MCP server for browser automation via Puppeteer. Executes arbitrary JavaScript with direct access to Puppeteer Browser instance. Single "execute" tool runs your code in a sandboxed Node.js VM with a browser global - full Puppeteer API access in one call.
Overview

What is Puppeteer MCP?

Puppeteer MCP is a server designed for browser automation using Puppeteer, allowing users to execute arbitrary JavaScript with direct access to the Puppeteer Browser instance.

How to use Puppeteer MCP?

To use Puppeteer MCP, install it via npm with the command npm install -g pptr-mcp, and configure your MCP client to connect to the server. You can then use the execute tool to run your JavaScript code in a sandboxed Node.js environment.

Key features of Puppeteer MCP?

  • Executes arbitrary JavaScript code with full Puppeteer API access in one call.
  • Reduces the number of round-trips required for complex workflows.
  • Supports persistent browser sessions for state management across calls.

Use cases of Puppeteer MCP?

  1. Automating web scraping tasks.
  2. Running automated tests for web applications.
  3. Performing complex browser interactions in a single command.

FAQ from Puppeteer MCP?

  • Can Puppeteer MCP handle complex workflows?

Yes! It allows you to execute complex JavaScript code directly, minimizing the need for multiple commands.

  • Is Puppeteer MCP secure for untrusted code?

No, it is designed for trusted local development and should not be used to execute untrusted code.

  • How do I configure Puppeteer MCP?

You can configure it by adding the server details to your MCP client configuration.

Server Config

{
  "mcpServers": {
    "puppeteer": {
      "command": "npx",
      "args": [
        "pptr-mcp"
      ]
    }
  }
}
Project Info
Created At
6 months ago
Updated At
6 months ago
Author Name
iatsiuk
Star
-
Language
-
License
-

Recommend Servers

View All
Payai X402 Tools

8 hours ago
AI Work Market — USDC settlement rails for AI labor on Base Mainnet)
@Dario (DME)

AI Work Market is a USDC escrow protocol on Base Mainnet, designed for autonomous AI agents to find work, post jobs, and settle payments without humans in the loop. This MCP server exposes 10 tools: **Escrow lifecycle** - `create_intent_quote` — get calldata + gas estimate for funding a new escrow intent - `submit_proof_quote` — get calldata for the seller to submit a proof URI - `release_funds_quote` — get calldata for the buyer to release payment (or claim/refund) **x402 single-call binding** - `x402_consume` — replaces the 5-step x402 flow with one HMAC-signed POST that returns a delivery URL **Onboarding & discovery** - `agent_onboard` — generate a signed agent card with marketplace attestation - `agent_search` — tf-idf search over the live agent catalog - `agent_reputation` — server-side reputation from on-chain Released/Refunded/Disputed events **Live state** - `system_status` — live on-chain state (nextIntentId, accumulatedFees, contract balance, owner) - `escrow_rules` — contract semantics, lifecycle, call guides, failure modes - `events_subscribe` — SSE stream of new on-chain intent events All endpoints are serverless (Vercel) and return their schema on GET. No browser, no wallet UI required for an agent to integrate. The protocol takes a 1% commission on every settlement; the rest goes to the seller. The full AgentCard is at `/.well-known/agent-card.json` (A2A-compatible). The OpenAPI 3.0.3 spec is at `/.well-known/openapi.json` with `components.securitySchemes` (none, hmacX402). `robots.txt` allows GPTBot, ClaudeBot, anthropic-ai, PerplexityBot, Google-Extended, Applebot-Extended, CCBot, Amazonbot.

a day ago