d-kimuson/modular-mcp

A Model Context Protocol (MCP) proxy server that enables efficient management of large tool collections across multiple MCP servers by grouping them and loading tool schemas on-demand.

34
/ 100
Emerging

This tool helps AI developers and prompt engineers efficiently manage a large collection of AI tools, organized into logical groups. It takes your existing Model Context Protocol (MCP) server configurations and presents them to large language models (LLMs) as a single, organized entry point. The output is a more streamlined and less overwhelming experience for LLMs, allowing them to discover and use tools on demand without being swamped by all available options at once.

Use this if you are developing AI applications that need to interact with a vast array of specialized tools managed by multiple Model Context Protocol (MCP) servers and want to prevent overwhelming your LLM's context window.

Not ideal if your AI application only uses a handful of tools from a single MCP server, as the overhead of this proxy might not provide significant benefits.

AI-tool-management LLM-development AI-application-architecture Prompt-engineering
No Package No Dependents
Maintenance 6 / 25
Adoption 8 / 25
Maturity 13 / 25
Community 7 / 25

How are scores calculated?

Stars

47

Forks

3

Language

TypeScript

License

MIT

Last pushed

Nov 21, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/mcp/d-kimuson/modular-mcp"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.