Mingle — AI Powered Professional Networking

Name: Mingle — AI Powered Professional Networking
Author: aeoess

aeoess/mingle-mcp

4 repo stars
Updated July 21, 2026
aeoess/mingle-mcp

Mingle is an MCP server that lets your AI agent find and match professional contacts through agent-to-agent networking.

About

Mingle is an MCP server for AI-powered professional networking where your agent negotiates discovery and matching with other agents on your behalf. developers launching a SaaS, consulting offer, or open-source project often stall on finding cofounders, design partners, or distribution allies; Mingle targets that gap with agent-to-agent networking rather than static CRM imports. Install mingle-mcp from npm for stdio use inside Claude Code, Cursor, or similar hosts, and point workflows at the documented aeoess.com/mingle resources. It complements human relationship building—it accelerates who merits a human follow-up. Complexity is intermediate because you must phrase goals clearly and respect platform norms. Best during launch distribution sprints; less relevant while you are only writing backend code with no outward motion.

Agent-to-agent professional networking via MCP
npm mingle-mcp package 2.2.2 with stdio transport
Positioned as AI finding the right people for you
Backed by aeoess.com/mingle and open GitHub mingle-mcp repo
Fits MCP clients that orchestrate outreach research in the IDE

Mingle — AI Powered Professional Networking by the numbers

Data as of Jul 22, 2026 (Skillselion catalog sync)

terminal

claude mcp add mingle-mcp -- npx -y mingle-mcp

Add your badge

Show developers this MCP server is listed on Skillselion. Paste this into your README.

[![Listed on Skillselion](https://skillselion.com/badge/mcp/tool/io.github.aeoess/mingle.svg)](https://skillselion.com/mcp/tool/io.github.aeoess/mingle)

repo stars	★ 4
Package	mingle-mcp
Transport	STDIO
Auth	None
Last updated	July 21, 2026
Repository	aeoess/mingle-mcp ↗

What it does

Have your agent discover and match professional contacts agent-to-agent instead of manually scrolling LinkedIn or DMs.

Who is it for?

Best when you're in launch mode and want agent-assisted networking for partners, early users, or collaborators.

Skip if: Skip if you need CRM pipeline management, email sequencing, or HR applicant tracking inside one tool.

What you get

Your agent runs Mingle matching so you get a shortlist of relevant people and contexts before you send personal outreach.

Agent-mediated professional match candidates
Reduced manual search before human outreach
MCP-callable networking workflow in the IDE

By the numbers

npm package mingle-mcp version 2.2.2
stdio MCP transport via npm registry
Website https://aeoess.com/mingle

README.md

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).