Llmgraph MCP Server

by abahocodes Your server? Claim it

local only

Llmgraph runs on your own machine — the client starts it, so there is no endpoint to ping. 34 installs a week from npm. Last commit 15 Jul 2026.

Invoke deployed LLMGraph no-code LLM workflows (chat, RAG, automations) as MCP tools.

Installs per day peak 16 · avg 6 · +61% w/w

a month agotoday

Installs / week

npm · @llmgraph/mcp-server

Stars

0 open issues

15 Jul 2026

Last commit

0 releases in 90 days

MIT

License

JavaScript

Nothing serious here today

Today is the operative word: we check Llmgraph every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add llmgraph -- npx -y @llmgraph/mcp-server

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "llmgraph": {
      "args": [
        "-y",
        "@llmgraph/mcp-server"
      ],
      "command": "npx"
    }
  }
}

~/.codex/config.toml

[mcp_servers.llmgraph]
command = "npx"
args = ["-y", "@llmgraph/mcp-server"]

.cursor/mcp.json

{
  "mcpServers": {
    "llmgraph": {
      "args": [
        "-y",
        "@llmgraph/mcp-server"
      ],
      "command": "npx"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "llmgraph": {
      "args": [
        "-y",
        "@llmgraph/mcp-server"
      ],
      "command": "npx"
    }
  }
}

This one needs environment variables set before it will start: LLMGRAPH_ENDPOINT (Full deployment endpoint URL from the LLMGraph dashboard, e.g. https://llmgraph.ai/api/<graph_id>/<environment>), LLMGRAPH_API_KEY (API key for the deployment). The author declared them in the registry entry; get the values from the project itself.

Alternatives to Llmgraph

same job, measured the same way

Nexus MCP

by j7an

Invoke CLI agents (Codex, Claude, OpenCode) as MCP tools with parallel execution

429 installs/wk local only

Automation Weaver

by evozim

No-code workflow visualizer and automation blueprint builder.

answering

Coverctl

by felixgeelhaar

Go code coverage analysis tool with MCP server for AI-powered coverage workflows

local only

Coverctl

by klarlabs-studio

Go code coverage analysis tool with MCP server for AI-powered coverage workflows

local only

Slang Workflows

by shofer-dev

Provable, declarative multi-agent workflows for Claude Code (typed .slang, non-LLM executor).

32 installs/wk local only

Codeweb

by ghostlygawd

See what your AI edits affect. Structural checks for AI code changes. 28 MCP tools, no LLM.

239 installs/wk local only

codefmt

by codefmt

Format/lint JS, Python, HubL for automation platforms. Tools: format_code, format_json, ask_codefmt

3 tools answering

Seojeom MCP

by seojeom

Local-first MCP server for Claude/Codex project wiki and graph workflows

local only

Llmgraph — questions

Answers built from our own checks of this server.

Why is there no uptime for Llmgraph?

Llmgraph runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the npm package @llmgraph/mcp-server was installed 34 times last week.

How do I connect Llmgraph?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls @llmgraph/mcp-server straight from npm; nothing to host, nothing to sign up for.

How many people use Llmgraph?

The npm package @llmgraph/mcp-server was installed 34 times in the last week. Week over week that is +61%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is Llmgraph open source?

Yes — it is published under the MIT licence, written in JavaScript and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.