OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
RAG & Knowledge Systems

Langconnect Client

A web GUI for managing PostgreSQL vector databases with pgvector, document search and Model Context Protocol integration.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Langconnect Client — OpenViST project profile in RAG & Knowledge Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when you need a graphical administration interface for a PostgreSQL/pgvector document collection and want MCP-enabled assistants to access its search or management tools.

Who it is for

  • Teams maintaining document collections in PostgreSQL with pgvector.
  • Developers connecting document search and collection-management workflows to MCP-capable assistants.

Documented uses

  • Create and manage collections with custom metadata.
  • Upload, organize and remove documents in supported formats.
  • Search documents semantically, by keyword or with hybrid retrieval.
  • Make collection, document and search operations available as MCP tools.
Before you choose

Requirements & limits

The README documents a self-hosted setup using Docker Compose, a Supabase account and configured Supabase credentials.

  • The documented database foundation is PostgreSQL with pgvector.
  • Supported document formats listed are PDF, TXT, MD, DOCX and HTML.
  • Semantic search uses OpenAI embeddings; keyword search uses PostgreSQL full-text search.
  • MCP configuration is documented for Claude Desktop and Cursor, with stdio and SSE transports.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up and start LangConnect Client with Docker Compose

Build the application and start its services for local access.

Before you start

  • Docker and Docker Compose
  • A Supabase account

Steps

  1. Clone the repository and enter its directory: the command below followed by cd langconnect-client.

    Documented command
    git clone https://github.com/teddynote-lab/langconnect-client.git

  2. Copy .env.example to .env, create a Supabase project, and set SUPABASE_URL and SUPABASE_KEY in .env using the project URL and anon public key.

  3. Build the Docker images with the command below.

    Documented command
    make build

  4. Start the services with the command below, then use the frontend at http://localhost:3000. Run the command below to stop them.

    Documented command
    make up
    Documented command
    make down

Expected outcome

The services are started, with the frontend listed at `http://localhost:3000`.

Guide limitations

  • The documented prerequisites also list Node.js 20+ for the MCP inspector and Python 3.11+ with UV; the quick start does not describe using the inspector.
  • The README describes PostgreSQL with pgvector, but does not provide configuration steps for a database backend.
  • The frontend URL is provided, but no specific GUI workflow for managing collections or documents is detailed.
Documentation 1 ↗
Source-based practical guide

Generate MCP configuration for Claude Desktop or Cursor

Generate the LangConnect MCP configuration and add it to an AI assistant's MCP settings.

Before you start

  • Docker and Docker Compose
  • A Supabase account and credentials

Steps

  1. From the repository directory, run the command below.

    Documented command
    make mcp

  2. Respond to the prompts for Supabase credentials; the command is described as obtaining an access token, updating .env, and generating mcpserver/mcp_config.json.

  3. For Claude Desktop, copy the contents of mcpserver/mcp_config.json into its MCP settings; for Cursor, add the configuration under MCP integrations.

Expected outcome

An MCP configuration file is generated and the README provides instructions to add it to Claude Desktop or Cursor.

Guide limitations

  • This recipe does not describe starting the application services; use the documented Docker Compose setup first if you need the running application.
  • No assistant-side verification or test procedure is provided.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Vector search

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
Langconnect ClientCreate and manage collections with custom metadata.Self-hosted, WebThe README documents a self-hosted setup using Docker Compose, a Supabase account and configured Supabase credentials.
Chatbot with PDF for Semantic SearchPrepare document content as embeddings and save it to a supported vector database.WebThe repository is identified as open source and publicly visible on GitHub.
AI LLM PlaygroundAsk questions about PDF documents through an assistant interface.Web
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
17 October 2026
Original website title
braincrew-lab/langconnect-client · Official homepage title · retained in its source language
How we review sourcesSuggest a correction