@rotifer/mcp-server
Self-evolving AI Agent framework — search, compare, and install Genes ranked by Arena fitness via MCP
@rotifer/mcp-server
Search, inspect, compare, and rank AI Genes — directly from your IDE.
MCP server for the Rotifer Protocol Gene ecosystem. Works with Cursor, Claude Desktop, Windsurf, and any MCP-compatible client.
Quick Start
Cursor
Add to .cursor/mcp.json:
{
"mcpServers": {
"rotifer": {
"command": "npx",
"args": ["-y", "@rotifer/mcp-server"]
}
}
}
Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"rotifer": {
"command": "npx",
"args": ["-y", "@rotifer/mcp-server"]
}
}
}
Windsurf / Other MCP Clients
Use the same npx command — any client that supports MCP stdio transport will work.
What Can It Do?
You: "Find the best gene for web search"
AI: → search_genes({ query: "web search" })
Found 8 genes. Top match: genesis-web-search (F(g) = 0.87, Native)
You: "Compare genesis-web-search vs genesis-web-search-lite"
AI: → compare_genes({ gene_ids: ["...", "..."] })
Side-by-side: success rate, latency, fitness breakdown
You: "What genes are installed locally?"
AI: → list_local_genes()
Found 5 genes in ./genes/
Tools
| Tool | Description |
|---|---|
search_genes | Search the Gene ecosystem by name, domain, or description |
get_gene_detail | Get detailed info about a specific Gene (phenotype, fitness, metadata) |
get_arena_rankings | Get Arena rankings for a domain, sorted by F(g) fitness score |
compare_genes | Side-by-side fitness comparison of 2–5 Genes |
get_gene_stats | Download statistics for a Gene (total, 7d, 30d, 90d) |
get_leaderboard | Developer reputation leaderboard |
get_developer_profile | Developer public profile and reputation data |
list_local_genes | Scan local workspace for installed Genes |
Resources
MCP Resources let AI clients reference Rotifer data as context:
| URI Template | Description |
|---|---|
rotifer://genes/{gene_id}/stats | Gene download statistics |
rotifer://genes/{gene_id} | Gene detail + phenotype |
rotifer://developers/{username} | Developer profile + reputation |
rotifer://leaderboard | Top developers by reputation score |
rotifer://local/genes | Local Gene inventory |
Architecture
┌─────────────────────────────────────────────────┐
│ AI IDE (Cursor / Claude / Windsurf) │
│ │
│ "Find genes for code formatting" │
│ │ │
│ ▼ │
│ ┌─────────────────────┐ │
│ │ MCP Client │ │
│ │ (stdio transport) │ │
│ └────────┬────────────┘ │
└───────────┼─────────────────────────────────────┘
│ MCP Protocol
▼
┌─────────────────────────────────────────────────┐
│ @rotifer/mcp-server │
│ │
│ Tools Resources Local Scanner │
│ ┌──────┐ ┌──────────┐ ┌───────────────┐ │
│ │search│ │gene://id │ │ ./genes/*.json │ │
│ │arena │ │dev://user│ │ phenotype scan │ │
│ │stats │ │leaderbd │ └───────────────┘ │
│ └──┬───┘ └────┬─────┘ │
└─────┼────────────┼──────────────────────────────┘
│ │
▼ ▼
┌─────────────────────────────────────────────────┐
│ Rotifer Cloud API (Supabase) │
│ genes · arena_entries · developer_reputation │
└─────────────────────────────────────────────────┘
Configuration
Zero-config by default — connects to the public Rotifer Cloud API.
To use a custom endpoint, create ~/.rotifer/cloud.json:
{
"endpoint": "https://your-supabase-instance.supabase.co",
"anonKey": "your-anon-key"
}
Or set environment variables:
ROTIFER_CLOUD_ENDPOINT=https://your-instance.supabase.co
ROTIFER_CLOUD_ANON_KEY=your-anon-key
Requirements
- Node.js >= 20
Links
- Rotifer Protocol — Main site
- MCP Setup Guide — Step-by-step setup
- Gene Marketplace — Browse and discover Genes
- Protocol Specification — Formal spec
- CLI Playground — Build and test Genes
License
Apache-2.0
相關伺服器
Scout Monitoring MCP
贊助Put performance and error data directly in the hands of your AI assistant.
Alpha Vantage MCP Server
贊助Access financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
VSCode MCP
Interact with VSCode through the Model Context Protocol, enabling AI agents to perform development tasks.
Create MCP App
Bootstrap Model Context Protocol (MCP) servers and clients in TypeScript with best practices, examples, and proper tooling setup.
Kestra Python MCP Server
A Python implementation of a Model Context Protocol server for interacting with Kestra.
Explorium API
Interact with the Explorium API to access external data for machine learning.
CLI Exec
Execute shell commands with structured output via a powerful CLI server.
Panther
Interact with the Panther security platform to write detections, query logs with natural language, and manage alerts.
Ant Design
Access comprehensive documentation for Ant Design components, including examples, API references, and best practices.
return0
Debug your remote Node.js and Next.js applications directly from your AI IDE like Cursor.
SumUp
Build card present and online payments solutions with SumUp.
BlenderMCP
Connects Blender to Claude AI via the Model Context Protocol (MCP), enabling direct AI interaction for prompt-assisted 3D modeling, scene creation, and manipulation.