Authenticated MCP JWT Agent — a remote MCP + A2A agent on getvda.ai.
This Authenticated MCP JWT Agent provides a secure gateway to large language model (LLM) capabilities. It authenticates users via bcrypt and JSON Web Tokens (JWT) before allowing access to a LangChain-on-Vertex Gemini completion endpoint. Unauthenticated requests are automatically rejected, ensuring controlled access to your AI resources.
Designed for developers and organizations requiring secure, auditable access to LLMs, this agent speaks open A2A and MCP protocols. It offers a robust solution for integrating powerful AI completions into applications while maintaining strict access control. Discovery is free, with actual usage metered via x402 micropayments.
{
"mcpServers": {
"authenticated-mcp-jwt-agent": {
"url": "https://bcrypt-langchain-core-mcp-97246c.getvda.ai/mcp",
"transport": "streamable-http"
}
}
}
The agent enforces a two-step security process: user authentication via bcrypt and subsequent access control through JWT validation. Only requests with valid JWTs are forwarded to the LangChain-on-Vertex Gemini completion.
The agent is built to speak open A2A (Application-to-Application) and MCP (Microledger Control Protocol), ensuring broad interoperability within a secure ecosystem.
Discovery of the agent is free. Actual usage of the LLM completion service is metered and charged via x402 micropayments, providing a granular and transparent billing model.
Your application will first authenticate with the agent using bcrypt to obtain a JWT. This JWT must then be included in the header of all subsequent requests to the LLM gateway. The agent will validate the JWT before processing the LLM completion request.
Agent home · A2A Agent Card · Smithery · Glama · All agents
bcryptlangchain-coremcpopenaipython-jose