convez.ai
MCP ServerAutomaçãoIntermediário
rotifer-protocol

Rotifer MCP Server

rotifer-protocol/rotifer-mcp-server

Crie e execute agentes IA compostos diretamente da sua IDE

Ver no GitHub
BomPluginScore · de 0 a 100

Servidor MCP que permite construir, compor e executar agentes de IA diretamente da IDE, com suporte a genomas compostos, sandbox WASM e arena competitiva. Integra-se com Cursor, Claude Desktop, Windsurf e qualquer cliente MCP compatível, oferecendo 29 ferramentas para descoberta, composição e execução de genes (unidades de IA).

Instalação

$npx convez-ai rotifer-protocol/rotifer-mcp-server

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
1
Forks
0
Acompanhando
0
Saúde
75%
Último commit
há 2 dias
Versão
v0.20.2
Issues abertas
1
Contribuidores
2

Casos de uso

  • Construir agentes customizados com composição de genes reutilizáveis
  • Pesquisar e comparar genes por fitness e desempenho
  • Executar pipelines em sandbox WASM sem configuração
  • Envolver funções existentes como genes publicáveis

Veredito

Ferramenta ambiciosa que democratiza a construção de agentes IA modular e componível. Promete zero-config e integração IDE nativa, mas a curva de aprendizado do modelo de genes e arena pode ser íngreme para iniciantes.

README

A tradução para o português deste README ainda está na fila.

@rotifer/mcp-server

npm License: Apache-2.0 Node.js MCP

Build, compose, and run AI agents — directly from your IDE.

Search genes, create agents with composable genomes, run pipelines in a WASM sandbox, and compete in the Arena. Zero config. Works with Cursor, Claude Desktop, Windsurf, and any MCP-compatible client.


Quick Start

Cursor

Add to .cursor/mcp.json:

{
  "mcpServers": {
    "rotifer": {
      "command": "npx",
      "args": ["@rotifer/mcp-server"]
    }
  }
}

Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "rotifer": {
      "command": "npx",
      "args": ["@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?

Create and run an agent in one conversation

You: "Build me an agent for code security scanning"
AI:  → create_agent({ agent_name: "sec-bot", gene_ids: ["security-scanner", "genesis-code-format"],
                       composition: "Seq" })
     Agent 'sec-bot' created with 2-gene Seq genome.

You: "Run it on my project"
AI:  → agent_run({ agent_name: "sec-bot", input: "{\"path\":\"./src\"}" })
     Pipeline complete — 3 findings, 0 critical.

Search, compare, and compose genes

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 it against the lite version"
AI:  → compare_genes({ gene_ids: ["...", "..."] })
     Side-by-side: success rate, latency, fitness breakdown

Full gene lifecycle from your IDE

You: "Wrap my function as a gene"
AI:  → wrap_gene({ gene_name: "my-search", domain: "search.web", fidelity: "Wrapped" })
     → compile_gene({ gene_name: "my-search" })
     → test_gene({ gene_name: "my-search", compliance: true })
     → publish_gene({ gene_name: "my-search", changelog: "Initial release" })

Tools (29)

Discovery & Analytics

ToolDescriptionKey Parameters
search_genesSearch the Gene ecosystem by name, domain, or descriptionquery, domain, fidelity, sort (relevance/newest/popular/fitness), page, per_page
get_gene_detailGet detailed info about a Gene (phenotype, fitness, metadata)gene_id, content_hash (either identifies the gene)
get_arena_rankingsArena rankings for a domain, sorted by F(g) fitnessdomain, page, per_page
compare_genesSide-by-side fitness comparison of 2–5 Genesgene_ids (array)
get_gene_statsDownload statistics (total, 7d, 30d, 90d)gene_id
get_leaderboardCreator reputation leaderboardlimit
get_developer_profileCreator public profile and reputationusername
get_gene_reputationDetailed reputation breakdown (Arena, Usage, Stability)gene_id
list_gene_versionsVersion history chain with changelogsowner, gene_name
suggest_domainSuggest matching domains from the registrydescription

Local Workspace

ToolDescriptionKey Parameters
list_local_genesScan local workspace for installed Genesproject_root, domain, fidelity
list_local_agentsList Agents in the local workspaceproject_root, state

Gene Lifecycle

ToolDescriptionKey Parameters
init_geneInitialize a new Gene project with starter filesgene_name, fidelity, domain, no_genesis
scan_genesScan for candidate functions or SKILL.md filespath, skills, skills_path
wrap_geneWrap a function/skill as a Genegene_name, domain, fidelity, from_skill, from_clawhub
test_geneTest a Gene (schema validation + sandbox)gene_name, verbose, compliance
compile_geneCompile a Gene to WASM IRgene_name, check, wasm_path, lang
run_geneExecute a local Genegene_name, input, verbose, no_sandbox, trust_unsigned
publish_genePublish to Rotifer Cloudgene_name, all, description, changelog, skip_arena, skip_security
install_geneInstall a Gene from Cloud Registrygene_id, project_root, force
vg_scanV(g) security scan — static analysis for Gene/Skill code safetypath, gene_id, all, project_root
arena_submitSubmit to Arena with 5D fitness scoresgene_id, fitness_value, safety_score, success_rate, latency_score, resource_efficiency

Agent Composition

ToolDescriptionKey Parameters
create_agentCreate an Agent composing multiple Genesagent_name, gene_ids, composition (Seq/Par/Cond/Try/TryPool), domain, top, strategy, par_merge
agent_runRun a local Agent by nameagent_name, input, verbose, no_sandbox

Authentication & Analytics

ToolDescriptionKey Parameters
auth_statusCheck login status—
loginOAuth login (GitHub/GitLab)provider, endpoint
logoutClear credentials—
get_mcp_statsMCP call analyticsdays
get_my_reputationCurrent user's reputation—

Resources (7)

MCP Resources let AI clients reference Rotifer data as context:

URI TemplateDescription
rotifer://genes/{gene_id}/statsGene download statistics
rotifer://genes/{gene_id}Gene detail + phenotype
rotifer://developers/{username}Creator profile + reputation
rotifer://leaderboardTop creators by reputation score
rotifer://local/genesLocal Gene inventory
rotifer://local/agentsLocal Agent registry
rotifer://versionMCP Server version and update availability

Prompts (4)

MCP Prompts give AI clients guided workflows for common tasks:

PromptDescriptionKey Arguments
rotifer-helloInteractive agent creation — pick a template and run immediatelytemplate, input
rotifer-guideUnderstand Rotifer Protocol — genes, agents, Arena, fidelity model—
rotifer-architectDesign an Agent — task-driven gene search + composition planningtask
rotifer-challengeArena evaluation — submit a gene, compare with competitorsgene

Try asking your AI: "Use the rotifer-hello prompt to build me an agent" or "Use rotifer-architect to design an agent for document Q&A".


Architecture

┌─────────────────────────────────────────────────┐
│  AI IDE (Cursor / Claude / Windsurf)            │
│                                                 │
│  "Find genes for code formatting"               │
│       │                                         │
│       ▼                                         │
│  ┌─────────────────────┐                        │
│  │  MCP Client         │                        │
│  │  (stdio transport)  │                        │
│  └────────┬────────────┘                        │
└───────────┼─────────────────────────────────────┘
            │ MCP Protocol
            ▼
┌─────────────────────────────────────────────────┐
│  @rotifer/mcp-server                            │
│                                                 │
│  29 Tools  7 Resources  4 Prompts  Local Scanner│
│  ┌──────────┐  ┌───────────┐   ┌────────────┐  │
│  │ discover │  │rotifer:// │   │ ./genes/    │  │
│  │ lifecycle│  │genes/stats│   │ phenotype   │  │
│  │ agents   │  │developers │   │ agents      │  │
│  │ auth     │  │leaderboard│   └────────────┘  │
│  └────┬─────┘  └─────┬─────┘         │         │
└───────┼──────────────┼────────────────┼─────────┘
        │              │                │
        ▼              ▼                ▼
┌─────────────────────────────────────────────────┐
│  Rotifer Cloud API          Local File System   │
│  (Supabase)                 (genes/, .rotifer/) │
└─────────────────────────────────────────────────┘

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

Pair with the CLI

This MCP server works best alongside the Rotifer CLI. The CLI provides the local runtime (WASM sandbox, Arena engine, IR compiler) while the MCP server exposes it all to your AI assistant:

npm install -g @rotifer/playground
rotifer init my-agent && cd my-agent
rotifer hello --template quality-advisor   # your first Agent workspace in seconds

Links

License

Apache-2.0

Ver o original no GitHub

Bom para

Relacionados