What does the Knowledge Base MCP Server do?
It provides tools for listing and retrieving content from different knowledge bases, supporting both MCP protocol access and a CLI for direct interaction.
@jeanibarz
Basic information
This MCP server provides tools for listing and retrieving content from different knowledge bases.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"knowledge-base-mcp-server": {
"command": "npx",
"args": [
"-y",
"@jeanibarz/knowledge-base-mcp-server@latest"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
Fetch the live tool list by running this server in a temporary sandbox using the button above.
It is an MCP server that provides tools for listing and retrieving content from different knowledge bases, accessible through both the MCP protocol and a CLI (kb). It is designed for AI agents and developers who need to search, retrieve, and manage local knowledge base content.
Install it via npx -y @jeanibarz/knowledge-base-mcp-server@latest or globally with npm install -g @jeanibarz/knowledge-base-mcp-server@latest. Configure environment variables like KNOWLEDGE_BASES_ROOT_DIR and FAISS_INDEX_PATH, then use the kb CLI for operations such as kb list, kb search, kb ask, and kb research. The MCP server runs over stdio by default.
It provides tools for listing and retrieving content from different knowledge bases, supporting both MCP protocol access and a CLI for direct interaction.
Use `npx -y @jeanibarz/knowledge-base-mcp-server@latest` to launch the server, or install globally with `npm install -g @jeanibarz/knowledge-base-mcp-server@latest` to use the `kb` CLI directly.
Node.js version 20 or higher and npm are required.
The MCP server uses stdio by default. Remote MCP transports are documented in the local service operations runbook.
Data location is configured via environment variables: `KNOWLEDGE_BASES_ROOT_DIR` for root directories, `FAISS_INDEX_PATH` for the FAISS index, and others for embedding providers.

Shared memory for AI coding agents. Claude Code, Cursor and Codex read your project's decisions, lessons and tasks before they act.
Memlord is a remote MCP server available at https://app.memlord.com.

The Cloud is the AI-native workspace that gives every AI — Claude, ChatGPT, Gemini, and other Frontier & Free or Local models — shared memory and real agents. Not cloud computing: thecloud.so is one workspace where your

Serve your docs to AI agents over SSH and MCP. Agents use ls, cat, grep, find, and pipes against a virtual filesystem backed by your documentation. Identity-scoped access, governed writing with human approval, and portab
Groundwork: company memory for your AI tools. Docs public. Source closed. Public proof needs no account.
Comments