- MCP-of-MCPS
MCP-of-MCPS
MCP of MCPs is a meta-server that merges all your MCP servers into a single smart endpoint. It gives AI agents instant tool discovery, selective schema loading, and massively cheaper execution, so you stop wasting tokens and time.
With persistent tool metadata, semantic search, and direct code execution between tools, it turns chaotic multi-server setups into a fast, efficient, hallucination-free workflow. It also automatically analyzes the tools output schemas if needed and preserves them across sessions for consistent behavior.
In short:
🚀 Faster automation
🧠 Cleaner reasoning
💰 Drastically fewer tokens
📦 Persistent + analyzed schema metadata
Overview
What is MCP of MCPs?
MCP of MCPs is a meta-server designed to aggregate multiple MCP servers, addressing issues of excessive token consumption, latency, and hallucinations in AI agents.
How to use MCP of MCPs?
To use MCP of MCPs, configure your MCP servers in the settings file and utilize its tools for efficient agent orchestration.
Key features of MCP of MCPs?
- Semantic Discovery Tool: Search tools by describing tasks in plain English.
- Discovery Tool: Get a lightweight overview of available tools without loading full schemas.
- Introspection Tool: Load only the necessary tools on-demand, saving tokens.
- Execution Tool: Execute workflows with direct data flow between tools, minimizing token usage.
Use cases of MCP of MCPs?
- Efficiently orchestrating complex workflows across multiple servers.
- Reducing token usage in AI agent operations.
- Enhancing accuracy by presenting only relevant information to models.
FAQ from MCP of MCPs?
- What problems does MCP of MCPs solve?
It reduces token consumption, speeds up execution, and minimizes hallucinations by providing relevant information only.
- Is it easy to set up?
Yes! It requires basic configuration of your MCP servers and can be integrated with existing setups.
- Can it handle multiple servers?
Yes! MCP of MCPs is designed to aggregate and manage multiple MCP servers efficiently.
Server Config
{
"mcpServers": {
"mcp-of-mcps": {
"autoApprove": [],
"disabled": false,
"timeout": 60,
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@dbestai/mcp-of-mcps",
"--config",
"[{\"name\":\"weather\",\"command\":\"npx\",\"args\":[\"-y\",\"@h1deya/mcp-server-weather\"]},{\"name\":\"time\",\"command\":\"uvx\",\"args\":[\"mcp-server-time\"]}]"
]
}
}
}Project Info
Created At
6 months agoUpdated At
6 months agoAuthor Name
eliavamarStar
-Language
-License
-Recommend Servers
View AllSigstore
@3089464667
a day ago
Rollinggo Hotel Mcp
@longcreat
2 days ago
Mcp Server Chatsum
@chatmcp
summarize chat message
typescript
a year ago
Filesystem
@modelcontextprotocol
2 months ago
Memory
@modelcontextprotocol
a year ago
Test
@modelcontextprotocol
test
6 months ago
Amap Maps
@amap
高德地图官方 MCP Server
a year ago