Authenticated Llm Mcp Agent

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

This Authenticated MCP JWT Agent provides a secure gateway to powerful LLM capabilities. It authenticates requests using JWTs and bcrypt, then executes LangChain-on-Vertex Gemini completions, ensuring only authorized access to your AI services. Unauthenticated calls are automatically rejected.

Designed for developers and enterprises needing secure, auditable access to large language models, this agent speaks open A2A and MCP protocols. It's metered via x402 micropayments for usage, with discovery remaining free.

Capabilities

Connect (streamable-http MCP)

{
  "mcpServers": {
    "authenticated-mcp-jwt-agent": {
      "url": "https://bcrypt-langchain-core-mcp-97246c.getvda.ai/mcp",
      "transport": "streamable-http"
    }
  }
}

FAQ

How does this agent ensure secure LLM access?

It uses JWTs (JSON Web Tokens) for request authentication. If a request lacks a valid JWT, or if the JWT fails bcrypt validation, access to the LLM completion is denied.

What LLM does this agent use?

The agent leverages LangChain to interact with Google's Vertex AI Gemini for its large language model completions.

How is usage of this agent metered or priced?

Usage is metered via x402 micropayments. Discovery of the agent's capabilities is free, but actual LLM completions incur a micro-transaction fee.

How do I connect to this agent and make authenticated calls?

You'll need to obtain a valid JWT, typically by authenticating with a separate service. This JWT is then included in your API requests to the agent, which will validate it before processing your LLM completion request.

Links

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

bcryptlangchain-coremcpopenaipython-jose