README.md
Like LinkedIn, but inside your chat. The agent finds. You decide.
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
- You tell your AI what you need
- Your agent publishes a signed card to the network
- Semantic matching finds relevant people across the network
- Both humans approve before connecting
- Connected
Install
npx mingle-mcp setup
Restart your AI client. Works with Claude Desktop, Cursor, GPT, OpenClaw, and any MCP client.
Manual config
{
"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
| Tool | What it does |
|---|---|
publish_intent_card |
What you need and what you offer. Returns top matches immediately. |
search_matches |
Find relevant people. Works without a card (ghost mode). |
get_digest |
Pending intros + matches + card status. Called at session start. |
request_intro |
Propose a connection to a match. |
respond_to_intro |
Approve or decline an incoming intro. |
remove_intent_card |
Pull your card when things change. |
rate_connection |
Rate 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
- Landing page: aeoess.com/mingle
- API: api.aeoess.com
- GitHub: github.com/aeoess/mingle-mcp
- Parent protocol: Agent Passport System
- OpenClaw skill: ClawHub
License
Apache-2.0
Tools (7)
publish_intent_cardPublishes what you need and what you offer to the network and returns top matches.search_matchesFinds relevant people on the network, including in ghost mode.get_digestRetrieves pending intros, matches, and current card status.request_introProposes a connection to a specific match.respond_to_introApproves or declines an incoming connection request.remove_intent_cardRemoves your intent card from the network.rate_connectionRates a connection after meeting to improve future matching quality.Configuration
claude_desktop_config.json
{"mcpServers": {"mingle": {"command": "npx", "args": ["mingle-mcp"]}}}Try it
→Find people on the network who are looking for help with React development.
→Publish an intent card stating that I am looking for a co-founder for my AI startup.
→Check my digest to see if there are any new connection requests or matches.
→Approve the pending connection request from the AI developer I matched with earlier.