Authenticated Llm Mcp Agent

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

This production-ready remote agent provides a secure and authenticated gateway to Google Vertex AI's Gemini LLM. It leverages LangChain for powerful completion capabilities, ensuring only authorized requests proceed after robust JWT and bcrypt authentication. All unauthenticated access is strictly rejected.

Designed for developers and organizations requiring secure, auditable, and metered LLM access, this agent speaks open A2A and MCP protocols. While discovery is free, all completions are metered via x402 micropayments, offering a transparent and efficient cost model for your AI interactions.

Capabilities

Connect (streamable-http MCP)

{
  "mcpServers": {
    "authenticated-mcp-traced-agent": {
      "url": "https://bcrypt-cryptography-langchain-cor-027cf2.getvda.ai/mcp",
      "transport": "streamable-http"
    }
  }
}

FAQ

How does the authentication process work for this agent?

The agent uses a two-tiered authentication system: bcrypt for secure password hashing during user registration, and JSON Web Tokens (JWT) to gate all subsequent LLM completion requests. Unauthenticated requests are rejected.

What is the pricing model for using this LLM agent?

While the discovery of the agent is free, all LLM completions are metered and charged via x402 micropayments. This ensures you only pay for the actual AI processing you consume.

How do I connect to and utilize this agent?

You connect to the agent via standard Open A2A and MCP protocols. After successful authentication (obtaining a valid JWT), you can send your LangChain-formatted prompts for Gemini completion.

What specific LLM is being used by this agent?

This agent utilizes Google Vertex AI's Gemini LLM for all its completion capabilities, accessed and orchestrated through LangChain.

Links

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

bcryptcryptographylangchain-coremcpopentelemetry-sdkpython-jose