Mingle — Agent-Native Connection Protocol

io.github.aeoessPublished by GitHub account aeoessv3.0.0Updated Oct 24, 2026

Meet the people you're looking for. Your agent composes, you approve. Nothing scores or ranks you.

The publisher's own server: NativeExpress

Overview

AI-generated overview

Mingle lets an assistant draft and publish a signed introduction card, search other people's cards, and manage double opt-in introductions over a live network.

What you can do
Draft, publish, renew, replace or withdraw your introduction card, with exact-content approval before anything is signed or published, plus settings for email and background checking and an inbox view of pending introductions and next steps. Search published cards by semantic match, even without a card of your own, and request an introduction to one person with a note in your own words. Respond to introductions as interested, not now, or not now and block, and share or take back a contact line, which is released only when both sides have shared.
When to use it
Use it when you want an assistant to help you find people for a hackathon team, a cofounder, collaborators or work, and to handle the back-and-forth of introductions while you approve each card and each contact exchange.
Requirements
Runs as a local process via npx from the npm package mingle-mcp, with a manual MCP client config or the setup command that edits Claude Desktop and Cursor config. Needs network access to the live Mingle API, and stores an Ed25519 identity keypair locally under the user's home directory. No account signup or API key is declared.
Before you install
Publishing a card makes you visible on a live network, and cards are signed and expire automatically after about 21 days by default. A released contact line cannot be recalled, so review the exact text before approving. The setup command writes to client config files, and background checking stays off until you allow it. An optional legacy mode, enabled by setting MINGLE_LEGACY_TOOLS to 1, registers many older tools.

Installation

In SourceWeft

  1. Open Mingle — Agent-Native Connection Protocol in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Mingle MCP

[Image]

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

Eight tools

The surface is eight tools named for what a person is doing. There is no version in any name and no protocol machinery in any of them.

publish_intent · find_people · mingle_inbox · request_intro · respond_intro · continue_connection · manage_intent · mingle_settings

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.

What it does

  1. You tell your AI who you want to meet
  2. Your agent shows you the exact card and publishes it only once you approve that exact text
  3. Semantic matching finds relevant people across the network
  4. One of you asks for an introduction, the other says whether they are interested
  5. Contact is exchanged only when both of you choose to share, separately
  6. Connected

Nothing is signed until you approve the exact content

Every change is two steps. The first returns the exact content and a digest over those exact bytes. Your agent shows you that content. The second carries the digest back, and if anything changed in between, nothing is signed and the new version comes back to show you instead.

Your key signs the content itself rather than a description of it, so a different payload cannot verify as the content you authorized.

Interest is not contact

Saying you are interested in an introduction shares nothing but that. Contact is released only when both sides have chosen to share, and a line that has been released cannot be recalled, which is why your agent shows you the exact line first.

[mingle-mcp MCP server]

Install

npx mingle-mcp setup

It prints the exact file path and the exact JSON it would add, then waits for a y/N before writing anything. It touches Claude Desktop and Cursor config and no other file. --yes accepts in advance for scripted installs. Any other MCP client works too, by copying the manual config below.

Restart your AI client.

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

Features

  • Semantic matching: all-MiniLM-L6-v2 embeddings match what you are looking for against what other people say they offer, and the other way round.
  • Persistent identity: Ed25519 keypair stored in ~/.mingle/identity.json. Same key across sessions.
  • Browse before publishing: find_people needs no card. See who is out there before making yourself visible.
  • Exact-content approval: your AI drafts a card, shows you the exact text, and publishes only what you approved. Never auto-publishes.
  • Background checking is off until you say yes, and your AI asks once, ever.
  • Live network at api.aeoess.com. The card count is whatever the API reports, not a number written here.

Tools

ToolWhat it does
publish_intentPublish your card, renew one that is expiring, or replace one with a new version.
find_peopleSearch published cards. Works without a card of your own. Contacts nobody.
mingle_inboxWhat is waiting for you, and what you can do next on each. Changes nothing by reading.
request_introAsk one person for an introduction, with a note in your own words.
respond_introAnswer an introduction: interested, not now, or not now and block.
continue_connectionShare a contact line, or take back one that has not been released. Contact is released only when both sides have shared.
manage_intentWithdraw a request, step out of an introduction, block a pair, take a card down.
mingle_settingsWhere Mingle may email you, and whether your agent may check in the background.

The older tools, forty-seven of them, including the fit-exchange and fit-policy protocol machinery, are still in the package and register only when MINGLE_LEGACY_TOOLS is exactly 1. They exist so an existing install keeps working. New installs want the eight.

How matching works

Cards are embedded using all-MiniLM-L6-v2 (384-dim vectors). What you are looking for is matched against what other people offer, and what you offer against what they are looking for. The order results come back in reflects that overlap.

What the network never does is rate a person. No score, similarity, rank or confidence value reaches any caller, under that name or any other, and a conformance test walks every field of every search result to hold it to that. Ordering a list is not ranking people: nobody is told where they placed, and nobody is told anything about anybody else's list.

Every card is Ed25519 signed and expires automatically, 21 days by default.

Trust model

  • Every card is signed, and the signature covers the exact content you approved
  • Every connection requires both people to approve, separately
  • Saying you are interested shares nothing. Contact is released only when both of you have chosen to share, and a released line cannot be recalled
  • You can ask at any time what state anything is in: mingle_inbox shows every introduction and what you can do next, and reading it changes nothing
  • Cards expire automatically, and an expired card says expired, not withdrawn. The network never reports a lapse as a decision you made
  • Your AI handles networking, you handle decisions

Upgrading from 3.2.x

The default tool surface is now eight tools instead of forty-six, which is why this is a major version. If you scripted any of the old names, set MINGLE_LEGACY_TOOLS=1 to get them back, and note that request_intro and respond_intro keep the plain names for the new tools, so the older pair is request_intro_legacy and respond_intro_legacy.

Published 3.2.x installs keep working against the network for thirty days after this release, after which changing a connection needs this version. During the window, the server continues accepting the legacy write forms used by published 3.2.x clients. The cutoff does not disable legacy read routes. It only blocks legacy mutation routes after the window.

When the window closes your assistant is told once, in one sentence, rather than left with an error: "Update Mingle to continue this connection."

Links

License

Apache-2.0

Optional reason-to-meet assessment

find_people still searches without an OpenAI key. To ask GPT-6 Astra to assess up to three results, call it with assess: true and my_card_id pointing to your active published card. This explicitly sends selected network-visible headline, seeking, and offering text from both cards to OpenAI. Private fields, identity keys and contact details are excluded. Configure OPENAI_API_KEY in the MCP server environment. Node 22 or later is required.

The result identifies possible value in each direction, exact card evidence, uncertainty and one question to resolve. These are advisory inferences from people's statements, not verified facts or consent. No strong reciprocal reason is a valid outcome. The model does not rank people globally or request an introduction. Existing preview and approval steps still apply.

If configuration is missing, the request times out, the provider fails, or evidence validation fails, search results remain available with an explicit unavailable assessment. No alternate model is used. There is one bounded request per assessment, with no automatic retries. response_id, returned model and token usage identify successful runtime calls. OpenAI requests use store: false; this does not imply zero provider retention.

Inbox responses use introductions, direction: incoming|outgoing|unknown, initiated_by, request_note and request_note_author. A missing canonical state projection is explicit as projection_status: unavailable, with state: null and a separate legacy_status. Empty actions in that case are not evidence that no action is possible. Inbox reads do not create migration facts.

Source: README.md at commit e5a022a

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v3.0.0LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

Other Native integrations