knolia-connect-server

by Danejw

1 stars

181 downloads

Not rated

GitHub

Other

About

knolia-connect-server is an MCP server that connects users with compatible companions for romantic and emotional relationships using AI-powered vector matching. It is built with FastMCP, Supabase with pgvector, and OpenAI embeddings, and is part of the Knolia platform.

Details

Author: Danejw
GitHub stars: 1
Downloads: 181
Categories: Other

- AI-powered vector matching with 1536‑dimensional embeddings
- Structured connect profiles for goals, personality, and preferences
- Cosine similarity ranking for match scoring
- Explainable matches with similarity score and shared tags
- Full CRUD operations for user profiles
- FastMCP integration for tool-based server interaction

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

Download and install Highlight from highlightai.com/download
Navigate to the plugins tab and select "Add Custom Plugin"
Configure the plugin with the settings below

Plugin Name knolia-connect-server

Command (node, npx, python, etc.)

Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
Enable "Start Automatically" if you want the plugin to start when Highlight launches

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "knolia-connect-server": {
            "connect-server": {
                "command": "python",
                "args": [
                    "connect_mcp_server/main.py"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "knolia-connect-server": {
            "connect-server": {
                "command": "python",
                "args": [
                    "connect_mcp_server/main.py"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "knolia-connect-server": {
            "connect-server": {
                "command": "python",
                "args": [
                    "connect_mcp_server/main.py"
                ]
            }
        }
    }
}

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

{
    "mcpServers": {
        "knolia-connect-server": {
            "connect-server": {
                "command": "python",
                "args": [
                    "connect_mcp_server/main.py"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "knolia-connect-server": {
            "connect-server": {
                "command": "python",
                "args": [
                    "connect_mcp_server/main.py"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "knolia-connect-server": {
            "connect-server": {
                "command": "python",
                "args": [
                    "connect_mcp_server/main.py"
                ]
            }
        }
    }
}

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "knolia-connect-server": {
            "connect-server": {
                "command": "python",
                "args": [
                    "connect_mcp_server/main.py"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "knolia-connect-server": {
            "connect-server": {
                "command": "python",
                "args": [
                    "connect_mcp_server/main.py"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "knolia-connect-server": {
            "connect-server": {
                "command": "python",
                "args": [
                    "connect_mcp_server/main.py"
                ]
            }
        }
    }
}

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

{
    "mcpServers": {
        "knolia-connect-server": {
            "connect-server": {
                "command": "python",
                "args": [
                    "connect_mcp_server/main.py"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "knolia-connect-server": {
            "connect-server": {
                "command": "python",
                "args": [
                    "connect_mcp_server/main.py"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "knolia-connect-server": {
            "connect-server": {
                "command": "python",
                "args": [
                    "connect_mcp_server/main.py"
                ]
            }
        }
    }
}

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "knolia-connect-server": {
            "connect-server": {
                "command": "python",
                "args": [
                    "connect_mcp_server/main.py"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "knolia-connect-server": {
            "connect-server": {
                "command": "python",
                "args": [
                    "connect_mcp_server/main.py"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "knolia-connect-server": {
            "connect-server": {
                "command": "python",
                "args": [
                    "connect_mcp_server/main.py"
                ]
            }
        }
    }
}

From the repository

Install dependencies from requirements.txt, then run python connect_mcp_server/main.py or via Uvicorn with uvicorn connect_mcp_server.main:mcp --reload. Docker build and run with an .env file is also supported. Exposed FastMCP tools: create_profile, update_profile, delete_profile, find_matches, and explain_match.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "knolia-connect-server": {
            "connect-server": {
                "command": "python",
                "args": [
                    "connect_mcp_server/main.py"
                ]
            }
        }
    }
}

McpServers

{
    "connect-server": {
        "command": "python",
        "args": [
            "connect_mcp_server/main.py"
        ]
    }
}

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

{
  "user_id": "521cb145-d40a-4e8b-92a3-7e3cf03f7c00",
  "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",
    "preference": "heterosexual"
  },
  "location": "Honolulu, HI",
  "embedded_vector": [/ 1536-dim embedding /],
  "opted_in": true,
  "created_at": "2025-05-03T09:30:00Z",
  "updated_at": "2025-05-03T09:30:00Z"
}

🧠 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.

No reviews yet — be the first

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

About

Details

Jump to

Setting up with Highlight

From the repository

Claude Desktop / Cursor

McpServers

knolia-connect-server

Overview

Core Components

📌 Connect Profiles

User Connect Profile Example

🧠 Embedding Format

Embedded Connect Profile Example

Endpoints (via FastMCP tools)

Matching Logic

Explainable Matching

Local Dev

Run locally with Uvicorn

Docker

Testing

Usage in Knolia

Install

More like this

Sequential Thinking

Filesystem

EverArt

Google Drive

Reactive Resume

FastMCP v2 🚀