Skip to content
mcp/harbor
Grok

authenticated llm agent for Grok

io.github.mikerawsonnz/authenticated-llm-agent

JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion.

client:Grok transport:streamable-http tools:2

Install authenticated llm agent in Grok

.mcp.json (in your project root) 

{
  "mcpServers": {
    "authenticated-llm-agent": {
      "type": "http",
      "url": "https://bcrypt-langchain-openai-mcp-bb738e.getvda.ai/mcp"
    }
  }
}

Grok Build reads Claude Code's .mcp.json and Claude Desktop's config unchanged, so a server you have already set up there needs nothing new. The Grok web app and X integration do not take custom servers. Grok docs

What Grok can do once it is connected

authenticated llm agent in other clients

authenticated llm agent MCP server