Llmgraph

Overview

Llmgraph is an MCP server that lets you invoke deployed LLMGraph no-code LLM workflows as tools within any MCP-compatible AI assistant. Whether you're building chat applications, RAG systems, or automations, your AI model can call these tools directly and decide when to use them during conversations or agent runs.

The server runs locally via the npm package @llmgraph/mcp-server using the command npx -y @llmgraph/mcp-server. You'll need to provide LLMGRAPH_ENDPOINT and LLMGRAPH_API_KEY as environment variables for authentication. Version v0.1.1 is available under the MIT license, with source code hosted at abahocodes/llmgraph-mcp-server on GitHub.

Llmgraph is categorized as an AI & Agents tool on mcp.site and works with all major MCP clients including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, and Zed. If you're the maintainer, you're welcome to claim this listing to verify ownership and keep the information up to date.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "llmgraph": {
      "command": "npx",
      "args": [
        "-y",
        "@llmgraph/mcp-server"
      ],
      "env": {
        "LLMGRAPH_ENDPOINT": "<llmgraph-endpoint>",
        "LLMGRAPH_API_KEY": "<llmgraph-api-key>"
      }
    }
  }
}

Requires LLMGRAPH_ENDPOINT, LLMGRAPH_API_KEY