# ThinkNEO Control Plane

ThinkNEO Control Plane is an MCP server for Claude Code that connects development assistants to an AI governance layer for spend audits, guardrail checks, and model health monitoring.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · 1024 installs
- Author: thinkneo-ai
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://smithery.ai/server/thinkneo-ai/control-plane
- Updated: 2026-03-23
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/thinkneo-ai-thinkneo-control-plane

## What it does

This server connects your AI client directly to the ThinkNEO gateway via `https://control-plane--thinkneo-ai.run.tools`. It lets your assistant check API usage expenses grouped by vendor or model, view threshold alerts, and verify hard budget caps inside the chat.

Teams can inspect prompts for policy violations with `thinkneo_evaluate_guardrail` before sending text upstream. It also exposes compliance readiness indicators for SOC2, GDPR, or HIPAA standards alongside workspace permission checks.

Almost all operations require active credentials in the ThinkNEO platform. Without authentication, the server only returns network metrics like latency and error rates through `thinkneo_provider_status` or accepts demo requests.

## Requirements
- Remote server: `https://control-plane--thinkneo-ai.run.tools`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http control-plane https://control-plane--thinkneo-ai.run.tools
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add thinkneo-ai-thinkneo-control-plane --url https://control-plane--thinkneo-ai.run.tools
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "thinkneo-ai-thinkneo-control-plane": {
            "url": "https://control-plane--thinkneo-ai.run.tools"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "thinkneo-ai-thinkneo-control-plane": {
            "type": "http",
            "url": "https://control-plane--thinkneo-ai.run.tools"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http thinkneo-ai-thinkneo-control-plane https://control-plane--thinkneo-ai.run.tools
```

## When to use it
- audit AI spend across teams, models, and selected periods
- evaluate user prompts against internal guardrails before submission
- verify workspace budget limits and forecast potential overages
- track real-time latency and error rates across AI providers

## Example prompts
- Check our current AI spend breakdown across OpenAI and Anthropic models.
- Evaluate this system prompt against our workspace guardrails.
- Show the current health and latency metrics for active AI providers.

## Similar
- [codex-control-plane-mcp](https://affpapa.org/en/nevibecode/skills/codex-control-plane-mcp.md) — skill · 100 installs
- [Codex Control Plane MCP](https://affpapa.org/en/nevibecode/mcp/codex-control-plane-mcp.md) — MCP server · ★ 114 repo stars
- [Control Plane](https://affpapa.org/en/nevibecode/mcp/control-plane.md) — MCP server · ★ 11 repo stars
- [Marrow AI: Control Layer for AI Agents](https://affpapa.org/en/nevibecode/mcp/marrow-ai-control-layer-for-ai-agents.md) — MCP server · ★ 7 repo stars
- [Creed Space](https://affpapa.org/en/nevibecode/mcp/creed-space.md) — MCP server · 10491 installs

## Other versions with the same name
- [ThinkNEO Control Plane · thinkneo-ai](https://affpapa.org/en/nevibecode/mcp/thinkneo-control-plane.md) — ★ 3 repo stars

---
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
