MCP ExplorerExplorer

Connect Server

@Danejwon a year ago
1 MIT
FreeCommunity
AI Systems
MCP server to connect users

Overview

What is Connect Server

Connect-server is an MCP server designed to connect users with compatible companions for romantic and emotional relationships through AI-powered vector matching.

Use cases

Use cases include helping users find emotionally compatible partners, enhancing matchmaking algorithms, and creating personalized relationship experiences based on user profiles.

How to use

Users can create, update, and delete their connection profiles using the provided FastMCP endpoints: create_profile, update_profile, and delete_profile.

Key features

Key features include structured user profiles that capture relationship goals, personality traits, and preferences, which are embedded as 1536-dimensional vectors for fast semantic matching.

Where to use

Connect-server is applicable in the dating and relationship-building sectors, particularly for platforms focused on fostering meaningful connections and reducing loneliness.

Content

knolia-connect-server

MCP server to connect users with compatible companions for romantic and emotional relationships using AI-powered vector matching.

Overview

The Knolia Connect MCP server powers deep and context-aware matchmaking for users seeking meaningful relationships. Built using FastMCP and backed by Supabase with pgvector, it allows users to create rich connection profiles that are embedded using OpenAI’s model and matched semantically to other users.

This service is part of Knolia’s mission to help users combat loneliness and emotional disconnection by fostering intentional and high-quality relationships.

Core Components

📌 Connect Profiles

Users who opt into Knolia Connect create a structured profile that captures their goals, personality, preferences, and values. This profile is embedded as a 1536-dimensional vector and stored for fast similarity-based matching.

User Connect Profile Example

🧠 Embedding Format

Before storage, all profile data is transformed into natural language for better semantic understanding.

Embedded Connect Profile Example

Relationship Goals:
Looking to build a deep emotional connection with someone who shares my values and growth mindset.

Personality Tags:
introverted, empathetic, spiritual

Sexual Preferences:
Gender: female
Orientation: heterosexual

Location:
Honolulu, HI

Endpoints (via FastMCP tools)

  • create_profile
  • update_profile
  • delete_profile
  • find_matches
  • explain_match

Matching Logic

Matches are found by retrieving all other embedded connect profiles and calculating the cosine similarity between the requesting user and other users. Matches are filtered and sorted by similarity score to find the most aligned companions.

Explainable Matching

The explain_match endpoint returns the similarity score between two users and any shared personality tags. This makes it clearer why a potential match was suggested.

Local Dev

pip install -r requirements.txt
python connect_mcp_server/main.py

Run locally with Uvicorn

python -m uvicorn connect_mcp_server.main:mcp --reload

Docker

docker build -t connect-mcp .
docker run -p 8002:8000 --env-file .env connect-mcp

Testing

Run Tests:

pytest

Usage in Knolia

Noelle, Knolia’s orchestrator, activates the Connect flow when a user opts into relationship discovery. Once opted in, their profile is embedded and compared against other matchable users. Noelle can then surface matches, initiate introductions, and facilitate conversation.


Built as part of the Knolia platform to bring meaningful connection to people ready for growth, companionship, and love.

Tools

No tools

Comments

Recommend MCP Servers

View All MCP Servers