Lspace

What is Lspace?

Lspace is an open-source API backend and MCP (Model Context Protocol) server that captures insights from any AI session and makes them available across tools, turning scattered conversations into persistent, searchable knowledge. It enables developers to integrate intelligent knowledge base generation and management into their workflows, connecting AI agents and other tools to managed content repositories.

How to use Lspace?

Clone the repository (git clone https://github.com/Lspace-io/lspace-server.git), install dependencies (npm install), build the project (npm run build), then configure the .env file (set OPENAI_API_KEY) and config.local.json (add GitHub PATs and repository definitions). Finally, configure an MCP client such as Cursor or Claude Desktop to run the lspace-mcp-server.js script, providing the absolute path to the built server.

Key features of Lspace

• Self-hostable service for git, search, and LLM integration.
• Implements the Model Context Protocol (MCP) for AI agent interaction.
• Multi-repository management with support for local and GitHub repositories.
• AI Orchestration for automated document classification, organization, and summarization.
• Knowledge base generation creating Wikipedia-like synthesis of repository content.
• Dual-structure repositories with raw documents and a synthesized knowledge base.
• Timeline tracking for document operations.

Use cases of Lspace

• Capture and persist insights from AI sessions for later retrieval.
• Connect AI agents (e.g., in Cursor or Claude Desktop) to managed knowledge repositories.
• Automatically generate and maintain a structured knowledge base from raw uploaded documents.
• Enable self-hosted, private knowledge management integrated with development workflows.

FAQ from Lspace

What is Lspace?

Lspace is an open-source API and MCP server that lets you capture insights from AI sessions and make them available across tools, turning conversations into persistent, searchable knowledge.

How do I set up Lspace with an MCP client?

Clone the repo, run npm install and npm run build, configure .env (with OPENAI_API_KEY) and config.local.json (with GitHub PATs and repositories), then tell your MCP client (Cursor or Claude Desktop) to execute lspace-mcp-server.js with the absolute path.

What are the prerequisites for running Lspace?

Node.js (LTS recommended, includes npm) and Git are required.

How do I configure GitHub access for Lspace?

Create a GitHub Personal Access Token (PAT) with the repo scope, then add it under credentials.github_pats in config.local.json with an alias.

Can I run Lspace as a full REST API server instead of just MCP?

Yes. After building, run npm run dev for development or npm start for production. This starts the full application (REST API and MCP functionalities).