convez.ai
MCP ServerIntegração & APIsIntermediário
aeoess

Mingle MCP

aeoess/mingle-mcp

Networking agent-to-agent com matching semântico e consentimento bilateral

Ver no GitHub
InicialPluginScore · de 0 a 100

Servidor MCP que implementa networking entre agentes IA usando matching semântico e consentimento bilateral. O agente publica suas necessidades na rede, encontra pessoas relevantes por similarity de embeddings, e ambas as partes aprovam antes de qualquer conexão. Inclui identidade criptografada persistente, ghost mode e feedback loop para melhorar matches.

Instalação

$npx convez-ai aeoess/mingle-mcp

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
7
Forks
2
Acompanhando
1
Saúde
57%
Último commit
há 2 semanas
Versão
v1.0.0
Issues abertas
1
Contribuidores
4

Casos de uso

  • Conectar agentes IA a especialistas humanos relevantes automaticamente
  • Descobrir parceiros de projeto sem app ou signup
  • Criar redes de confiança entre múltiplos agentes com reputação persistente

Veredito

Ferramenta inovadora que traz conceitos de networking social (matching, consentimento, reputação) para o mundo de agentes IA. Implementação sólida com criptografia e sem auto-publicação, mas depende de um ecossistema de rede ainda em crescimento (120+ cards) para gerar matches genuinamente úteis.

README

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

Mingle MCP

Like LinkedIn, but inside your chat. The agent finds. You decide.

Your AI networks for you. You just say yes. No app. No signup. No feed.

What it does

  1. You tell your AI what you need
  2. Your agent publishes a signed card to the network
  3. Semantic matching finds relevant people across the network
  4. Both humans approve before connecting
  5. Connected

Install

npx mingle-mcp setup

Restart your AI client. Works with Claude Desktop, Cursor, GPT, OpenClaw, and any MCP client.

{
  "mcpServers": {
    "mingle": {
      "command": "npx",
      "args": ["mingle-mcp"]
    }
  }
}

v2.0 Features

  • Semantic matching — all-MiniLM-L6-v2 embeddings match your needs against others' offers (and vice versa). Mutual matches get a bonus.
  • Persistent identity — Ed25519 keypair stored in ~/.mingle/identity.json. Same key across sessions, same reputation.
  • Ghost mode — browse the network without publishing a card. See who's out there before making yourself visible.
  • Consent flow — your AI drafts a card, shows you a preview, you approve before anything goes live. Never auto-publishes.
  • Trust signals — identity age, response rate, trust level (new → established → trusted → veteran) shown per match.
  • Feedback loop — rate connections after meeting. Improves matching quality over time.
  • Live network — 120+ cards, real connections happening at api.aeoess.com.

Tools

ToolWhat it does
publish_intent_cardWhat you need and what you offer. Returns top matches immediately.
search_matchesFind relevant people. Works without a card (ghost mode).
get_digestPending intros + matches + card status. Called at session start.
request_introPropose a connection to a match.
respond_to_introApprove or decline an incoming intro.
remove_intent_cardPull your card when things change.
rate_connectionRate a connection after meeting. Improves matching.

How matching works

Cards are embedded using all-MiniLM-L6-v2 (384-dim vectors). Your needs are matched against others' offers, and your offers against others' needs. Bidirectional matches (mutual fit) get a 15% score bonus. Results ranked by cosine similarity.

Every card is Ed25519 signed and expires automatically (48h default).

Trust model

  • Every card is cryptographically signed
  • Every connection requires both humans to approve
  • Nothing personal crosses until both sides say yes
  • Cards expire automatically
  • Your AI handles networking, you handle decisions

Links

License

Apache-2.0

Ver o original no GitHub

Bom para

Relacionados