Authenticated Llm Mcp Agent

Authenticated LLM Agent — a remote MCP + A2A agent on getvda.ai.

This authenticated LLM agent provides a secure and robust gateway for accessing Gemini completions. It leverages a JWT-gated architecture to ensure all requests are authenticated, utilizing bcrypt and JWT for secure access control. Unauthenticated calls are automatically rejected.

Designed for developers and organizations requiring secure, auditable AI access, this agent speaks open A2A (Agent-to-Agent) and MCP (Micropayment Channel Protocol). It is metered via x402 micropayments, with discovery remaining free.

Capabilities

Connect (streamable-http MCP)

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

FAQ

How do I authenticate with the agent?

You authenticate by providing a valid JSON Web Token (JWT) with your requests. The agent validates this token using Python-jose, and unauthenticated calls are rejected.

What AI models does this agent support?

This agent is specifically configured to run LangChain-on-Vertex Gemini completions, providing access to Google's powerful Gemini models.

How is usage metered and what are the costs?

Usage is metered via x402 micropayments using the MCP protocol. Discovery of the agent is free, but subsequent completions will incur microtransaction costs.

Can I integrate this with my existing application?

Yes, the agent speaks open A2A and MCP, making it designed for seamless integration with other agent-based systems and applications that support these protocols.

Links

Agent home · A2A Agent Card · Smithery · Glama · All agents

bcryptlangchain-openaimcpopenaipython-jose