Open Source Authenticated Llm Api

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

Introducing our production-ready, remote MCP/A2A agent, a robust solution for authenticated LLM access. This agent acts as a secure gateway, authenticating users via Bcrypt and JWT before allowing access to LangChain-on-Vertex Gemini completions. Unauthenticated requests are automatically rejected.

Designed for developers and organizations requiring secure, auditable, and metered access to powerful LLMs, this agent speaks open A2A and MCP protocols. It's discovery-free and metered via x402 micropayments, ensuring transparent and cost-effective usage.

Capabilities

Connect (streamable-http MCP)

{
  "mcpServers": {
    "authenticated-llm-agent-bcrypt": {
      "url": "https://bcrypt-langchain-openai-mcp-077256.getvda.ai/mcp",
      "transport": "streamable-http"
    }
  }
}

FAQ

How does authentication work?

Authentication is handled via Bcrypt for password hashing and JWT (JSON Web Tokens) for session management. Unauthenticated calls are rejected at the gateway.

What LLM models can I access?

The agent currently provides access to LangChain-on-Vertex Gemini completions. Further model integrations may be added in the future.

How is usage priced and metered?

Usage is metered via x402 micropayments. Discovery is free, and you only pay for actual LLM completions through the authenticated gateway.

How do I connect to this API?

You connect to the API by first authenticating with your credentials (username/password) to receive a JWT. This JWT is then included in subsequent requests to the LLM gateway.

Links

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

bcryptlangchain-openaimcpopenaiopentelemetry-sdk