ThinkNEO Control Plane · thinkneo-ai — Claude Code MCP server: setup guide
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.
no license 1,024 installs updated 2026-03-23
claude mcp add --transport http control-plane https://control-plane--thinkneo-ai.run.toolsWhat ThinkNEO Control Plane 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.
What it helps with
- 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 for the agent
- 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.
How to install ThinkNEO Control Plane
Platform CLI: remote server
claude mcp add --transport http control-plane https://control-plane--thinkneo-ai.run.toolsPlatform CLI: remote server
codex mcp add thinkneo-ai-thinkneo-control-plane --url https://control-plane--thinkneo-ai.run.toolsConfig file
{
"mcpServers": {
"thinkneo-ai-thinkneo-control-plane": {
"url": "https://control-plane--thinkneo-ai.run.tools"
}
}
}Config file
{
"servers": {
"thinkneo-ai-thinkneo-control-plane": {
"type": "http",
"url": "https://control-plane--thinkneo-ai.run.tools"
}
}
}Platform CLI: remote server
gemini mcp add -t http thinkneo-ai-thinkneo-control-plane https://control-plane--thinkneo-ai.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 ThinkNEO Control Plane
How to install ThinkNEO Control Plane in Claude Code?
Run claude mcp add --transport http control-plane https://control-plane--thinkneo-ai.run.tools in your terminal.
What does ThinkNEO Control Plane do?
It exposes tools to monitor AI expenses, enforce workspace prompt policies, verify regulatory compliance scores, and review upstream provider uptime.
Is an API key required to run the tools?
Tools inspecting spend, budgets, policies, and compliance require authentication. Monitoring uptime and latency with thinkneo_provider_status works without any account credentials.
Similar MCP servers
All MCP servers for AI and ML →ThinkNEO Control Plane by other authors comes first.