Authenticated LLM Agent — Claude Code MCP server: features and setup
The Authenticated LLM Agent MCP server checks JWT credentials before sending a request to Gemini through LangChain and Vertex. Its separate self-test tool returns a sample result and trust details.
no license 2,349 installs updated 2026-05-31
claude mcp add --transport http authenticated-llm-agent https://authenticated-llm-agent--a2a.run.toolsWhat Authenticated LLM Agent does
The invoke tool checks a password with bcrypt and validates JWT credentials before requesting a Gemini completion through LangChain on Vertex. Requests without authentication are rejected. Access checks are part of the call flow.
Use selftest to run the agent on a fixed input. It returns the actual result, an assertion grade, and trust information: a signed Agent Card, JWKS, a governance and licence chain, and a safety posture. Each claim has a proof link. The test is free and requires no payment.
What it helps with
- gate LLM requests behind JWT authentication
- reject calls that lack valid authentication
- run the agent against a fixed test input
- inspect trust claims alongside proof links
Example prompts for the agent
- Use
invoketo send a Gemini request after JWT authentication. - Run
selftestwith its fixed input and show me the result. - Show the assertion grade and proof links returned by
selftest.
How to install Authenticated LLM Agent
Platform CLI: remote server
claude mcp add --transport http authenticated-llm-agent https://authenticated-llm-agent--a2a.run.toolsPlatform CLI: remote server
codex mcp add authenticated-llm-agent --url https://authenticated-llm-agent--a2a.run.toolsConfig file
{
"mcpServers": {
"authenticated-llm-agent": {
"url": "https://authenticated-llm-agent--a2a.run.tools"
}
}
}Config file
{
"servers": {
"authenticated-llm-agent": {
"type": "http",
"url": "https://authenticated-llm-agent--a2a.run.tools"
}
}
}Platform CLI: remote server
gemini mcp add -t http authenticated-llm-agent https://authenticated-llm-agent--a2a.run.toolsStep by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about Authenticated LLM Agent
How do I install Authenticated LLM Agent in Claude Code?
Run claude mcp add --transport http authenticated-llm-agent https://authenticated-llm-agent--a2a.run.tools.
What does Authenticated LLM Agent do?
It authenticates requests before calling Gemini through LangChain and Vertex. A separate tool runs a self-test and returns trust information.
What does selftest return?
It provides the result from a fixed input, an assertion grade, and a trust manifest with a signed Agent Card, JWKS, governance and licence details, safety information, and proof links.