Steel MCP Server

Created By
MCP-Mirrora year ago
Mirror of
Overview

What is Steel MCP Server?

Steel MCP Server is a Model Context Protocol (MCP) server that allows large language models (LLMs) like Claude to perform web automation tasks using Puppeteer-based tools. It is built on the Web Voyager framework and provides functionalities for standard web actions such as clicking, scrolling, typing, and taking screenshots.

How to use Steel MCP Server?

To use Steel MCP Server, you need to clone the repository, install the necessary dependencies, and configure it with Claude Desktop. You can run it in either cloud mode or local mode depending on your setup.

Key features of Steel MCP Server?

  • Browser automation capabilities using Puppeteer.
  • Integration with Steel for managing browser sessions.
  • Visual element identification through numbered labels.
  • Screenshot capturing functionality.
  • Support for basic web interactions like navigation, clicking, and form filling.
  • Local and remote Steel instance support.

Use cases of Steel MCP Server?

  1. Automating online tasks such as searching for recipes or tracking package deliveries.
  2. Filling out online forms and applications.
  3. Comparing prices for products across different websites.

FAQ from Steel MCP Server?

  • Can Steel MCP Server run locally?
    Yes, it can run in both local and cloud modes depending on your configuration.

  • What are the prerequisites for using Steel MCP Server?
    You need to have Git, Node.js, and Claude Desktop installed, along with optional Steel Docker image for self-hosting.

  • Is there a way to manage sessions?
    Yes, you can view and manage active Steel Browser sessions through the Steel dashboard.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
MCP-Mirror
Star
-
Language
-
License
-

Recommend Servers

View All
Voyei

2 hours ago
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago