knolia-connect-server
@Danejw
About knolia-connect-server
MCP server to connect users
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"connect-server": {
"command": "python",
"args": [
"connect_mcp_server/main.py"
]
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is knolia-connect-server?
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.
How to use knolia-connect-server?
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.
Key features of knolia-connect-server?
- 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
Use cases of knolia-connect-server?
- Matching users seeking deep emotional connections based on values and personality
- Facilitating introductions between compatible companions
- Providing transparency through explainable match suggestions
- Helping combat loneliness via intentional relationship discovery
FAQ from knolia-connect-server
What dependencies are required?
Python packages in requirements.txt, a Supabase database with pgvector, and an OpenAI API key for embedding generation.
How are matches computed?
Cosine similarity between each user’s 1536‑dimensional embedding and the embeddings of all other opted‑in users.
What data is stored?
User profile data (relationship goals, personality tags, sexual preferences, location, embedded vector, opt‑in status) in Supabase.
What transport does the server use?
—
Can I run knolia-connect-server locally?
Yes. Install dependencies, set environment variables, and run via Uvicorn or Docker as described in the README.
Frequently asked questions
What dependencies are required?
Python packages in `requirements.txt`, a Supabase database with `pgvector`, and an OpenAI API key for embedding generation.
How are matches computed?
Cosine similarity between each user’s 1536‑dimensional embedding and the embeddings of all other opted‑in users.
What data is stored?
User profile data (relationship goals, personality tags, sexual preferences, location, embedded vector, opt‑in status) in Supabase.
Can I run knolia-connect-server locally?
Yes. Install dependencies, set environment variables, and run via Uvicorn or Docker as described in the README.
Basic information
More Other MCP servers
AutoBrowser MCP
autobrowser-aiBrowser MCP is a Model Context Provider (MCP) server that allows AI applications to control your browser
Mcp
browsermcpBrowser MCP is a Model Context Provider (MCP) server that allows AI applications to control your browser
DeepMark
DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.
🪟 Windows-MCP
CursorTouchMCP Server for Computer Use in Windows
Reactive Resume
amruthpillaiA one-of-a-kind resume builder that keeps your privacy in mind. Completely secure, customizable, portable, open-source and free forever. Try it out today!
Comments