Llmgraph runs on your own machine — the client starts it, so there is no endpoint to ping. 35 installs a week from npm. Last commit 15 Jul 2026.
Invoke deployed LLMGraph no-code LLM workflows (chat, RAG, automations) as MCP tools.
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 mcp add llmgraph -e 'LLMGRAPH_ENDPOINT=<LLMGRAPH_ENDPOINT>' -e 'LLMGRAPH_API_KEY=<LLMGRAPH_API_KEY>' -- npx -y @llmgraph/mcp-server{
"mcpServers": {
"llmgraph": {
"command": "npx",
"args": [
"-y",
"@llmgraph/mcp-server"
],
"env": {
"LLMGRAPH_API_KEY": "<LLMGRAPH_API_KEY>",
"LLMGRAPH_ENDPOINT": "<LLMGRAPH_ENDPOINT>"
}
}
}
}[mcp_servers.llmgraph]
command = "npx"
args = ["-y", "@llmgraph/mcp-server"]
env = { LLMGRAPH_ENDPOINT = "<LLMGRAPH_ENDPOINT>", LLMGRAPH_API_KEY = "<LLMGRAPH_API_KEY>" }{
"mcpServers": {
"llmgraph": {
"command": "npx",
"args": [
"-y",
"@llmgraph/mcp-server"
],
"env": {
"LLMGRAPH_API_KEY": "<LLMGRAPH_API_KEY>",
"LLMGRAPH_ENDPOINT": "<LLMGRAPH_ENDPOINT>"
}
}
}
}{
"servers": {
"llmgraph": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@llmgraph/mcp-server"
],
"env": {
"LLMGRAPH_API_KEY": "<LLMGRAPH_API_KEY>",
"LLMGRAPH_ENDPOINT": "<LLMGRAPH_ENDPOINT>"
}
}
}
}Put your own values in place of
<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’s registry entry marks them as required.
Alternatives to Llmgraph
same job, measured the same wayConvert Make and Zapier automations into n8n workflows, with a report of what to check.
No-code workflow visualizer and automation blueprint builder.
Go code coverage analysis tool with MCP server for AI-powered coverage workflows
Go code coverage analysis tool with MCP server for AI-powered coverage workflows
Provable, declarative multi-agent workflows for Claude Code (typed .slang, non-LLM executor).
See what your AI edits affect. Structural checks for AI code changes. 28 MCP tools, no LLM.
Local-first MCP server for Claude/Codex project wiki and graph workflows
Inter-agent communication for multi-agent Claude Code workflows.
Llmgraph — questions
Answers built from our own checks of this server.