thinkneo-control-plane

thinkneo-control-plane

Enterprise AI governance layer for spend tracking, runtime guardrails, policy enforcement, and budget limits. Connects Claude, ChatGPT, and any MCP client to ThinkNEO's control plane for SOC2/GDPR/HIPAA compliance monitoring and real-time provider health.

Category
访问服务器

README

ThinkNEO MCP Server

License: MIT MCP Website Glama

Enterprise AI Control Plane — Remote MCP server for ThinkNEO.

Enables Claude, ChatGPT, Copilot, Gemini, and any MCP-compatible client to interact directly with ThinkNEO's governance capabilities: spend tracking, guardrail evaluation, policy enforcement, budget monitoring, compliance status, and provider health.

  • Registry: ai.thinkneo/control-plane
  • Endpoint: https://mcp.thinkneo.ai/mcp
  • Transport: streamable-http
  • Auth: Bearer token (ThinkNEO API key) for protected tools

Tools

Tool Description Auth
thinkneo_check_spend AI cost breakdown by provider/model/team Required
thinkneo_evaluate_guardrail Pre-flight prompt safety evaluation Required
thinkneo_check_policy Verify model/provider/action is allowed Required
thinkneo_get_budget_status Budget utilization and enforcement Required
thinkneo_list_alerts Active alerts and incidents Required
thinkneo_get_compliance_status SOC2/GDPR/HIPAA readiness Required
thinkneo_provider_status Real-time AI provider health Public
thinkneo_schedule_demo Book a demo with ThinkNEO Public

Connect in Claude Desktop

Add to ~/.claude/claude_desktop_config.json (macOS/Linux) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

With authentication (full access):

{
  "mcpServers": {
    "thinkneo": {
      "url": "https://mcp.thinkneo.ai/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_THINKNEO_API_KEY>"
      }
    }
  }
}

Public tools only (no API key):

{
  "mcpServers": {
    "thinkneo": {
      "url": "https://mcp.thinkneo.ai/mcp"
    }
  }
}

To get your ThinkNEO API key, request access at thinkneo.ai/talk-sales or email hello@thinkneo.ai.


Connect in VS Code (GitHub Copilot)

Add to .vscode/mcp.json in your workspace or user settings:

{
  "servers": {
    "thinkneo": {
      "type": "http",
      "url": "https://mcp.thinkneo.ai/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_THINKNEO_API_KEY>"
      }
    }
  }
}

Test with curl

List available tools (no auth required):

curl -X POST https://mcp.thinkneo.ai/mcp \
  -H "Content-Type: application/json" \
  -d '{
    "jsonrpc": "2.0",
    "method": "tools/list",
    "id": 1,
    "params": {}
  }'

Check provider status (public tool):

curl -X POST https://mcp.thinkneo.ai/mcp \
  -H "Content-Type: application/json" \
  -d '{
    "jsonrpc": "2.0",
    "method": "tools/call",
    "id": 2,
    "params": {
      "name": "thinkneo_provider_status",
      "arguments": {"provider": "openai"}
    }
  }'

Check AI spend (requires Bearer token):

curl -X POST https://mcp.thinkneo.ai/mcp \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer <YOUR_API_KEY>" \
  -d '{
    "jsonrpc": "2.0",
    "method": "tools/call",
    "id": 3,
    "params": {
      "name": "thinkneo_check_spend",
      "arguments": {
        "workspace": "prod-engineering",
        "period": "this-month",
        "group_by": "provider"
      }
    }
  }'

Evaluate a prompt against guardrails (requires Bearer token):

curl -X POST https://mcp.thinkneo.ai/mcp \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer <YOUR_API_KEY>" \
  -d '{
    "jsonrpc": "2.0",
    "method": "tools/call",
    "id": 4,
    "params": {
      "name": "thinkneo_evaluate_guardrail",
      "arguments": {
        "text": "Summarize this document for me",
        "workspace": "prod-engineering",
        "guardrail_mode": "enforce"
      }
    }
  }'

Self-hosted Deployment

Prerequisites

  • Docker + Docker Compose
  • Nginx reverse proxy (for HTTPS)

Quick start

git clone https://github.com/thinkneo-ai/mcp-server.git
cd mcp-server

# Configure environment
cp .env.example .env
# Edit .env: set THINKNEO_MCP_API_KEYS and THINKNEO_API_KEY

# Build and start
docker compose up -d

# Verify
curl -X POST http://localhost:8081/mcp \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","method":"tools/list","id":1,"params":{}}'

Nginx configuration (HTTPS at mcp.thinkneo.ai)

server {
    listen 443 ssl;
    server_name mcp.thinkneo.ai;

    ssl_certificate /etc/letsencrypt/live/mcp.thinkneo.ai/fullchain.pem;
    ssl_certificate_key /etc/letsencrypt/live/mcp.thinkneo.ai/privkey.pem;

    location /mcp {
        proxy_pass http://127.0.0.1:8081/mcp;
        proxy_http_version 1.1;
        proxy_set_header Host $host;
        proxy_set_header X-Real-IP $remote_addr;
        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
        proxy_set_header X-Forwarded-Proto $scheme;
        # Required for streamable-http (keep connection open)
        proxy_buffering off;
        proxy_read_timeout 300s;
        proxy_send_timeout 300s;
    }
}

Publish to MCP Registry

Option A — DNS authentication (recommended, uses ai.thinkneo/control-plane namespace)

# 1. Generate Ed25519 key pair
openssl genpkey -algorithm Ed25519 -out /tmp/thinkneo-mcp-key.pem

# 2. Get the public key value for the DNS TXT record
PUB=$(openssl pkey -in /tmp/thinkneo-mcp-key.pem -pubout -outform DER | tail -c 32 | base64)
echo "Add DNS TXT record to thinkneo.ai:"
echo "  Host: _mcp"
echo "  Type: TXT"
echo "  Value: v=MCPv1; k=ed25519; p=${PUB}"

# 3. Wait for DNS propagation (usually 5-30 minutes), then publish
mcp-publisher publish \
  --registry-url "https://registry.modelcontextprotocol.io" \
  --mcp-file "./server.json" \
  --auth-method dns \
  --dns-domain thinkneo.ai \
  --dns-private-key /tmp/thinkneo-mcp-key.pem

Option B — GitHub authentication (simpler, uses io.github.thinkneo-ai/control-plane namespace)

mcp-publisher login github
mcp-publisher publish \
  --registry-url "https://registry.modelcontextprotocol.io" \
  --mcp-file "./server.json"

Option C — GitHub Actions (automated on tag push)

See .github/workflows/publish-mcp.yml for the full CI/CD workflow.


Verify registry listing

# Search
curl -s "https://registry.modelcontextprotocol.io/v0/servers?search=thinkneo" | jq .

# Direct lookup
curl -s "https://registry.modelcontextprotocol.io/v0/servers/ai.thinkneo%2Fcontrol-plane" | jq .

License

This project is licensed under the MIT License.


Related

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选