Claude MCP Server

Created By
Surfer12a year ago
Overview

What is Claude MCP Server?

Claude MCP Server is a server implementation that adheres to the Model Context Protocol (MCP), allowing for standardized integration of various AI tools and models, including those from OpenAI, Anthropic, and Google.

How to use Claude MCP Server?

To use the server, clone the repository, set up environment variables for your preferred AI provider, and run either the Node.js or Python server. You can interact with the server using MCP-compliant clients via JSON-RPC 2.0 protocol.

Key features of Claude MCP Server?

  • MCP Compliance: Seamless integration with MCP clients.
  • Multi-Provider Support: Works with OpenAI, Anthropic, and Google models.
  • Extensible Tooling: Framework for adding custom tools like code generation and web scraping.
  • Node.js and Python Implementations: Offers both server options.
  • Docker Support: Easy deployment and development.
  • Comprehensive Testing: Integrated testing with Jest and pytest.

Use cases of Claude MCP Server?

  1. Integrating multiple AI models for diverse applications.
  2. Automating code generation and analysis tasks.
  3. Facilitating web interactions and data scraping.
  4. Supporting development environments with containerization.

FAQ from Claude MCP Server?

  • Can I use my own AI models with Claude MCP Server?

Yes! You can configure the server to use your own models by setting the appropriate environment variables.

  • Is there support for custom tools?

Yes! The server includes a framework for adding and managing custom tools easily.

  • How do I deploy Claude MCP Server?

The recommended way is to use Docker for consistent and isolated deployment.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
Surfer12
Star
-
Language
-
License
-

Recommend Servers

View All
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