WebSocket MCP

Created By
zeropointoa year ago
Model Context Protocol (MCP) server and client with a custom websocket transport layer.
Overview

What is WebSocket MCP?

WebSocket MCP is a project that implements a websockets-based Model Context Protocol (MCP) server and client, designed to enhance communication between clients and local LLMs (Large Language Models).

How to use WebSocket MCP?

To use WebSocket MCP, you can run the server and client using command-line arguments. The server can be started with default settings for local operation, and the client can connect to the server to send prompts and receive responses.

Key features of WebSocket MCP?

  • Robust MCP server implementation for efficient message exchange.
  • Generic MCP client for interacting with servers, supporting resource listing and data streaming.
  • Local LLM server for generating responses based on prompts.
  • Flexibility to support various LLM models and configurations.

Use cases of WebSocket MCP?

  1. Building interactive applications that require real-time communication with LLMs.
  2. Developing chatbots that utilize local LLMs for generating responses.
  3. Facilitating data streaming and resource management in applications using LLMs.

FAQ from WebSocket MCP?

  • What is the purpose of the WebSocket MCP?

The purpose is to create a better MCP implementation that overcomes limitations of standard transport layers.

  • Is WebSocket MCP easy to set up?

Yes! It can be configured and run using simple command-line commands.

  • Can I use different LLM models with WebSocket MCP?

Yes! The project is designed to be flexible and supports various LLM models.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
zeropointo
Star
0
Language
Python
License
MIT 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