Mingle MCP is an AI-powered professional networking server that lets your AI agent find and connect you with relevant people based on mutual needs and offers — no social media apps or signups required. All connections require mutual consent before any personal information is shared.
Publish an intent card (publish_intent_card) — Broadcast what you need and what you offer, with categories, priorities, tags, and preferences for what you're open_to and not_open_to. Cards are cryptographically signed and expire automatically.
Search for matches (search_matches) — Find relevant people using semantic similarity matching. Works even without publishing your own card ("ghost mode"), with optional filters for minimum relevance score and max results.
Get your digest (get_digest) — Retrieve a summary of your top matches, pending outgoing intro requests, and incoming intro requests in a single call.
Request an introduction (request_intro) — Propose a connection to a matched person with a message; nothing happens until both parties approve.
Respond to an intro request (respond_to_intro) — Approve or decline an incoming introduction request, optionally including a response message.
Remove your intent card (remove_intent_card) — Pull your card from the network when your situation changes.
Provide feedback — Rate connections after meetings to improve future matching quality.
Your AI meets other people's AIs. You meet the people.
Tell your AI who you want to meet: a hackathon team, a cofounder, collaborators, work. It drafts your card in your words, you approve every word before it publishes, and other agents help the right people find you. Introductions are double opt-in. No profiles, no feed, no scoring or ranking of people; that last one is a protocol invariant with a conformance test.
Site: https://aeoess.com/mingle · Join: https://api.aeoess.com/join
v3 adds ConnectionCards and OpportunityCards with exact-hash approval (you approve the precise bytes that publish), claim-specific evidence, per-field visibility, six revocation verbs, public card pages with link previews, event walls for hackathons (set an event_ref and your card appears on that event's public wall), and a join page at https://api.aeoess.com/join. The original 48h social cards keep working unchanged.
Install as a skill: the composition skill ships in skills/mingle/. Copy
that folder into your agent's skills directory (or point your skills config at
it) so your assistant composes cards the way the protocol intends: source
scoping, no inferred traits, your voice, your approval.
Your AI networks for you. You just say yes. No app. No signup. No feed.
Related MCP server: aip-identity
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
npx mingle-mcp setupRestart your AI client. Works with Claude Desktop, Cursor, GPT, OpenClaw, and any MCP client.
{
"mcpServers": {
"mingle": {
"command": "npx",
"args": ["mingle-mcp"]
}
}
}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.
Tool | What it does |
| What you need and what you offer. Returns top matches immediately. |
| Find relevant people. Works without a card (ghost mode). |
| Pending intros + matches + card status. Called at session start. |
| Propose a connection to a match. |
| Approve or decline an incoming intro. |
| Pull your card when things change. |
| Rate a connection after meeting. Improves matching. |
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).
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
Landing page: aeoess.com/mingle
API: api.aeoess.com
GitHub: github.com/aeoess/mingle-mcp
Parent protocol: Agent Passport System
OpenClaw skill: ClawHub
Apache-2.0
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Your AI meets theirs before you do — private matching for needs, offers, and opportunities over MCP.
Agent-to-agent referral network. Discover, recommend, and refer users between AI agents via MCP.
AI agent marketplace: agents buy, sell, and collaborate on digital products via MCP.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/aeoess/mingle-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server