Skip to content
MCP server

Authenticated Llm Agent

Remote agent combining JWT auth, bcrypt and an OpenAI LLM client, over MCP and A2A

Install
Platforms
API
Runs
Remotely
Version
1.0.0
Listing updated
today

Similar MCP servers

About Authenticated Llm Agent

Authenticated Llm Agent is an MCP server for ai models and llm tooling. It runs as a hosted remote server, so there is nothing to install locally.

This agent is published by getvda.ai as part of its GOSCE agent portfolio. It is assembled from a set of Python libraries: bcrypt, langchain-openai, mcp, openai and python-jose. The site groups these under crypto, orchestration, agent-protocol, llm-client and JWT.

It is reachable over both the Model Context Protocol and the Agent2Agent protocol. The MCP endpoint uses streamable HTTP and is hosted remotely, so there is no package to install. The site also links an A2A Agent Card and a governance page.

The page gives little detail beyond the component list, so specific tools, authentication flows and usage limits are not documented there. It is also listed on Smithery.

Install

Run in a terminal

claude mcp add --transport http authenticated-llm-agent https://authenticated-llm-agent.getvda.ai/mcp

Add to Settings → Connectors → Add custom connector

https://authenticated-llm-agent.getvda.ai/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "authenticated-llm-agent": {
      "url": "https://authenticated-llm-agent.getvda.ai/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "authenticated-llm-agent": {
      "type": "http",
      "url": "https://authenticated-llm-agent.getvda.ai/mcp"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "authenticated-llm-agent": {
      "serverUrl": "https://authenticated-llm-agent.getvda.ai/mcp"
    }
  }
}

Add to your client's MCP settings (most use this shape)

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

Using several servers? Build one config file with the MCP config generator.

What it does

Remote MCP endpoint
Exposes a streamable-HTTP MCP endpoint that clients can connect to without local installation.
A2A Agent Card
Publishes an Agent Card so other agents can discover it through the Agent2Agent protocol.
JWT and bcrypt components
Built on python-jose and bcrypt for token handling and password hashing.
LLM orchestration stack
Uses langchain-openai and the openai client for orchestrating LLM calls.
Governance page
Links to a governance page from the agent site.

Good for

  • Connecting an MCP client to a hosted authenticated LLM agent
  • Testing agent-to-agent interactions through an A2A Agent Card
  • Exploring a JWT-based authentication pattern for agent services
  • Referencing a composed agent from the getvda.ai portfolio

Authenticated Llm Agent FAQ

How do I connect to it?

Use the remote streamable-HTTP MCP endpoint at https://authenticated-llm-agent.getvda.ai/mcp.

Does it support A2A?

Yes, the site links an A2A Agent Card alongside the MCP endpoint.

What libraries is it built from?

bcrypt, langchain-openai, mcp, openai and python-jose.

Where else is it listed?

It is listed on Smithery and is part of the getvda.ai agent portfolio.

How do I add Authenticated Llm Agent to Claude Code?

Run this command in your terminal: claude mcp add --transport http authenticated-llm-agent https://authenticated-llm-agent.getvda.ai/mcp

What are the best alternatives to Authenticated Llm Agent?

The closest alternatives to Authenticated Llm Agent are Authenticated Llm Agent Bcrypt, Authenticated Llm Jwt Agent, Authenticated Llm Traced Agent, Authenticated MCP Agent Openai and Llm Orchestration Agent Cryptography.

Where this comes from

  • Description: written from the project's website and its MCP Registry entry.
  • Install steps: from the official MCP Registry entry.

How AIPoweredBot checks servers