# Secured LangChain OpenAI Agent

The Secured LangChain OpenAI Agent MCP server for Claude Code provides a token-protected gateway for LangChain model executions.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · 2894 installs
- Author: a2a
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://smithery.ai/server/a2a/authenticated-mcp-agent
- Updated: 2026-05-31
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/secured-langchain-openai-agent

## What it does

This remote service packages LangChain orchestration, OpenAI tooling, and OpenTelemetry observability behind access controls. Calls require authentication, rejecting unauthorized requests before hitting model endpoints.

Two operations are exposed. The `invoke` handler verifies JWT credentials prior to dispatching tasks to Vertex Gemini completions. The complimentary `selftest` tool processes a predefined check to verify readiness, outputting JWKS records, assertion scores, and agent verification metadata.

## Requirements
- Remote server: `https://authenticated-mcp-agent--a2a.run.tools`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http authenticated-mcp-agent https://authenticated-mcp-agent--a2a.run.tools
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add secured-langchain-openai-agent --url https://authenticated-mcp-agent--a2a.run.tools
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "secured-langchain-openai-agent": {
            "url": "https://authenticated-mcp-agent--a2a.run.tools"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "secured-langchain-openai-agent": {
            "type": "http",
            "url": "https://authenticated-mcp-agent--a2a.run.tools"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http secured-langchain-openai-agent https://authenticated-mcp-agent--a2a.run.tools
```

## When to use it
- gate agent completions behind cryptographic tokens
- validate agent operational health using signed manifests
- route completions through an authenticated LangChain gateway

## Example prompts
- Run selftest to inspect the agent signature and manifest
- Execute invoke with an authorized token to process a prompt

## Similar
- [LangSmith Traced OpenAI Agent](https://affpapa.org/en/nevibecode/mcp/langsmith-traced-openai-agent.md) — MCP server · 4178 installs
- [langchain-rag](https://affpapa.org/en/nevibecode/skills/langchain-rag.md) — skill · 18600 installs
- [langchain-fundamentals](https://affpapa.org/en/nevibecode/skills/langchain-fundamentals.md) — skill · 18500 installs
- [Authenticated LLM Agent](https://affpapa.org/en/nevibecode/mcp/authenticated-llm-agent.md) — MCP server · 2349 installs
- [agents-langchain](https://affpapa.org/en/nevibecode/skills/agents-langchain.md) — skill · 968 installs
- [langchain-dev-guide](https://affpapa.org/en/nevibecode/skills/langchain-dev-guide.md) — skill · 895 installs

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
