MCPchat

Created By
postfixa year ago
MCPchat is terminal-based LLM chat client supporting multiple Model Context Protocol (MCP) servers with real-time server management and dynamic model switching.
Overview

what is MCPchat?

MCPchat is a terminal-based chat client that connects to multiple Model Context Protocol (MCP) servers, allowing users to interact with various language model providers through a unified interface.

how to use MCPchat?

To use MCPchat, clone the repository, install the dependencies, configure the environment variables with your MCP server details, and start the application using the command npm start.

key features of MCPchat?

  • Multi-server support for simultaneous connections to various MCP servers.
  • Dynamic model switching to change between different models on the fly.
  • Real-time health monitoring of server connections.
  • Session management to maintain chat history and context.
  • User-friendly terminal interface with color-coded messages.
  • Full TypeScript support with schema validation for type safety.
  • Comprehensive logging for debugging and monitoring.

use cases of MCPchat?

  1. Engaging in conversations with different language models.
  2. Managing multiple chat sessions across various MCP servers.
  3. Monitoring server health and performance in real-time.

FAQ from MCPchat?

  • Can MCPchat connect to any MCP server?

Yes! MCPchat supports connections to any server that implements the Model Context Protocol.

  • Is there a graphical user interface for MCPchat?

No, MCPchat is designed as a terminal-based application for users who prefer command-line interfaces.

  • How do I switch between models?

You can use the /switch command to change to a different server or model during a chat session.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
postfix
Star
0
Language
-
License
BSD-3-Clause 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