MCP Browser

Created By
neoforge-deva year ago
NeoForge Browser MCP server - used to test the frontend
Overview

what is MCP Browser?

MCP Browser is a headless browser interface designed for the Model Control Protocol (MCP), enabling automated browser interactions and real-time updates.

how to use MCP Browser?

To use MCP Browser, clone the repository, set up the environment, and run the application either locally or via Docker.

key features of MCP Browser?

  • Headless browser automation using Playwright
  • Web UI for browser interaction
  • WebSocket communication for real-time updates
  • Integration with MCP for AI agents

use cases of MCP Browser?

  1. Automating web interactions for testing purposes.
  2. Real-time data updates for AI applications.
  3. Facilitating browser-based automation tasks in a headless environment.

FAQ from MCP Browser?

  • What are the prerequisites for using MCP Browser?

You need Python 3.13+, Docker, and the uv dependency manager.

  • How can I run MCP Browser locally?

You can run it locally by following the setup instructions in the repository and executing the provided test scripts.

  • Is MCP Browser suitable for production use?

Yes, it can be deployed using Docker for production environments.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
neoforge-dev
Star
1
Language
Python
License
-
Tags

Recommend Servers

View All
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.

21 minutes ago