vMCP - Virtual Model Context Protocol
Lego for AI workflows and agents: An open-source tool for composing, customizing and extending multiple MCP servers into a single logical, virtual MCP server
Built for fine grained context-engineering
- Create vMCP, Add MCP servers and Fine-tune
- Extend with your own prompts, tools and resources
- Connect any client (Claude, ChatGPT, Gemini, Cursor, VScode, custom agents) to the vMCP
- Create multiple logical vMCPs based on your workflow and agent needs
vMCP (virtual Model Context Protocol) is an AI configuration and management platform built on top of the Model Context Protocol. It is both :
- A specification that builds on and extends MCPs: vMCP.json
- A platform to create and deploy vMCP Servers:
<div align="center" <img src="https://raw.githubusercontent.com/1xn-labs/1xn-vmcp/main/.assets/img/vmcp-intro-screen.png" alt="1xn vMCP Platform" width="780"/ </div
Why We Built This
The Model Context Protocol has unlocked incredible possibilities for AI integrations, but users and developers quickly hit limitations:
- Configuration Hell: Managing MCP configs across multiple clients (Claude, ChatGPT, VSCode, Cursor, Gemini) is tedious
- Auth: Each mcp client needs its own auth for all the MCPs
- Lack of Customization: Can't modify or extend existing MCPs for specific workflow needs - "context rot / confusion"
- No Composition: Building complex workflows requires piecing together multiple tools from multiple MCPs
vMCP solves these problems by providing a layer of abstraction and a no-code configuration interface on top of standard MCPs.
Highlight Features
- Flexible vMCP Creation: Compose different MCP servers into a unified MCP server with a simple no-code interface.
- Context Engineering with MCPs:
- 🛠️ Customizable Tools: Select and override tool names/descriptions from upstream MCPs and prefill tool arguments.
- ✨ Extensible Tooling: Create new tools using Python, REST APIs or plain text (Prompt tools).
- 🗣️ Programmable Prompts: Define prompts that can invoke other tools and resources, enabling user-controlled tool chaining.
- 🔗 Add files as resources: Select MCP resource and add your own knowledge base files
- MCP Server Authentication: Authorize MCP servers once and re-use across clients (Claude, Cursor, ChatGPT, VSCode, Gemini, AI agents)
- Usage Statistics: Track and analyze vMCP usage patterns with full MCP protocol level logging
- Docker and PyPi Ready: Official Docker images for easy deployment. uv and pip command for quick trial
<div align="center" <img src="https://raw.githubusercontent.com/1xn-labs/1xn-vmcp/main/.assets/img/vmcp-arch.png" alt="vMCP Architecture" width="780"/ </div
🚀 Quickstart
Prerequisites
vMCP requires Python 3.10 to 3.13 and uv.