MCP Router

Created By
codewithkenzoa year ago
MCP Router: A web interface for orchestrating MCP servers with Upsonic agent framework integration
Overview

What is MCP Router?

MCP Router is a Python package designed for managing Model Context Protocol (MCP) servers, integrating with the OpenRouter LLM framework, and orchestrating complex workflows using the Upsonic agent framework.

How to use MCP Router?

To use MCP Router, clone the repository, install the required dependencies, and either use it as a module in your Python scripts or run the command line interface (CLI) for server management tasks.

Key features of MCP Router?

  • MCP Server Management: Add, edit, and remove MCP servers.
  • OpenRouter Integration: Query OpenRouter models for AI-assisted tasks.
  • Upsonic Integration: Create and manage complex workflows.
  • Intelligent Task Analysis: Automatically determine necessary tools for tasks.
  • API Framework: Expose functionalities via REST API endpoints.

Use cases of MCP Router?

  1. Managing multiple MCP servers for AI applications.
  2. Automating workflows that require multiple steps and tools.
  3. Integrating AI models into applications for enhanced functionality.

FAQ from MCP Router?

  • What is the minimum Python version required?

Python 3.8 or higher is required to run MCP Router.

  • Can I run MCP servers without Docker?

Yes, Docker is optional but recommended for easier management of MCP servers.

  • How can I contribute to MCP Router?

Contributions are welcome! Fork the repository, create a feature branch, and submit a Pull Request.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
codewithkenzo
Star
0
Language
TypeScript
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