ThinkNEO Control Plane

ai.thinkneo由 thinkneo.ai 發布官方發布者v1.29.0更新於 Oct 24, 2026

Enterprise AI Control Plane: governance, guardrails, spend tracking, compliance & smart routing.

已驗證Streamable HTTP可網頁執行雲端與基礎設施安全與監控AI 與機器學習

概覽

AI 產生的概覽

面向企業 AI 治理的遠端 MCP 伺服器，提供 72 個工具，涵蓋護欄、支出追蹤、路由、可觀測性、合規與安全。

可以做什麼
對 AI 使用與代理活動執行治理與護欄檢查、策略引擎規則和信任評分，並提供治理稽核與策略預檢提示。追蹤支出與成本（FinOps），將請求路由到供應商和模型，並管理供應商與模型登錄表。監控使用情況與可觀測性，驗證結果，對代理進行基準測試，並匯出稽核紀錄。透過 ThinkShield 規則包進行安全偵測，涵蓋注入、驗證濫用、偵察和標頭異常。以代理控制技能將 MCP 橋接到 Google A2A 協定，另含快取、記憶、排程和告警工具。
適用情境
適合組織希望讓助理圍繞 AI 與代理活動執行策略、護欄和支出控制，或從單一端點檢視治理、合規與安全訊號的情境。對只需要通用工具的個人使用者意義不大。
執行需求
遠端 streamable HTTP 端點 mcp.thinkneo.ai；清單未宣告驗證、環境變數或標頭。README 提到每月 500 次呼叫的免費額度並自動配置 API 金鑰，也支援透過 git clone、pip install 和 uvicorn 或 Docker 自行架設。
安裝前請注意
README 說明治理編排、稽核鏈、租戶管理和企業整合屬於專有部分，執行於 thinkneo.ai，因此部分功能依賴該第三方服務。免費額度為每月 500 次呼叫，並提到付費計費。許多工具面向治理、安全和稽核，可能記錄或匯出活動資料；使用前請確認會傳送哪些內容到遠端服務。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 ThinkNEO Control Plane，將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/ai.thinkneo%2Fcontrol-plane/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "thinkneo-control-plane": {
      "type": "http",
      "url": "https://mcp.thinkneo.ai/mcp"
    }
  }
}

README

ThinkNEO MCP Server

Open MCP server with built-in defense layer (ThinkShield). Part of the ThinkNEO Platform — enterprise AI governance.

[License: Apache-2.0] [MCP Protocol] [A2A Protocol] [Tools] [A2A Skills] [Glama AAA] [Tests]

What This Is

An open-source MCP server providing 72 tools for AI governance, observability, and security:

  • ThinkShield — Production defense layer: detection engine, 5 rule packs, runtime middleware. 145 tests, p99 < 1ms.
  • 72 MCP Tools — Governance, guardrails, FinOps, smart routing, observability, compliance, outcome validation, and more.
  • 24 A2A Skills — Bidirectional MCP-A2A bridge for Google's Agent-to-Agent Protocol (v0.3.0, Linux Foundation).
  • Apache-2.0 — Use it, fork it, contribute.

What This Is Not

  • Not the full ThinkNEO Platform. Governance orchestration, cryptographic audit chain, tenant management, and enterprise integrations are proprietary and run at thinkneo.ai.
  • Not a standalone security product. ThinkShield is the defense component of a larger governed platform.

Why Open

We open-source our defense layer because real security doesn't depend on hidden rules — it depends on tested, audited, continuously improved detection plus a strong governance moat around it.

Snort. Suricata. Falco. OWASP CRS. The security industry runs on open detection. We follow that tradition.

The detection is open. The governance is proprietary. That's where the moat is.

Architecture

                        Open Source (this repo)                    Proprietary (thinkneo.ai)                   ┌─────────────────────────────────┐     ┌──────────────────────────────────┐                   │                                 │     │                                  │  MCP Clients ────>│  72 MCP Tools                   │     │  Governance Orchestration         │  (Claude, Cursor, │  ├── Guardrails & Safety        │────>│  ├── Policy Engine (AIRGP)        │   ChatGPT, etc.)  │  ├── FinOps & Smart Routing     │     │  ├── Cryptographic Audit Chain    │                   │  ├── Observability              │     │  ├── Tenant Management            │  A2A Agents ─────>│  ├── Compliance & Validation    │     │  ├── Enterprise Integrations      │  (Google A2A)     │  └── MCP-A2A Bridge (24 skills) │     │  └── SLA & Support                │                   │                                 │     │                                  │                   │  ThinkShield Defense Layer       │     │  SHA-256 Hash Chain (949K+ rows)  │                   │  ├── Detection Engine            │     │  Stripe Billing                   │                   │  ├── 5 Rule Packs               │     │  Resend Email                     │                   │  └── ASGI Middleware             │     │  Multi-tenant Auth                │                   │                                 │     │                                  │                   └─────────────────────────────────┘     └──────────────────────────────────┘                          Apache-2.0 License                      Commercial License

Quickstart

bash
# Clonegit clone https://github.com/thinkneo-ai/mcp-server.gitcd mcp-server
# Installpip install -r requirements.txt
# Runpython -m uvicorn src.server:app --host 0.0.0.0 --port 8081
# Testpython -m pytest tests/ -q

Or with Docker:

bash
cd deploydocker compose up -d

Connect from Claude Desktop, Cursor, or any MCP client:

https://mcp.thinkneo.ai/mcp

Free tier: 500 calls/month, auto-provisioned API key. All 72 tools available.

Components

DirectoryDescriptionLicense
src/tools/72 MCP tools — governance, security, FinOps, observabilityApache-2.0
src/thinkshield/Defense layer — detection engine, 5 rule packsApache-2.0
tests/thinkshield/ThinkShield test suite — 145 tests + attack/benign fixturesApache-2.0
agent.jsonA2A Agent Card — 24 skills bridged from MCPApache-2.0

ThinkShield Rule Packs

PackDetects
injectionSQL injection, XSS, command injection, path traversal
authCredential stuffing, brute force, token replay, privilege escalation
abuseRate abuse, resource exhaustion, API scraping
reconPath probing, tool enumeration, method probing, fingerprinting
headersHeader anomalies, spoofing, missing security headers

MCP Tools (72)

Governance (6) | Guardrails (3) | FinOps (4) | Smart Router (4) | Trust Score (2) | Registry (5) | Bridge (4) | Observability (5) | Business Value (6) | A2A Control (4) | Optimization (1) | Outcome Validation (4) | Policy Engine (4) | Benchmarking (3) | Compliance (2) | Agent SLA (4) | Audit Export (3) | Cache (3) | Security (5) | Tokens (1) | Memory (2) | Scheduling (1) | Alerts (1)

Full tool reference: docs/quickstart.md

MCP Spec Compliance

Complete Model Context Protocol 2024-11-05 implementation. Forward-compatible with MCP 2025-03-26.

CapabilityStatusDetails
tools72 tools, full annotationsdestructiveHint, readOnlyHint, idempotentHint, openWorldHint
resources2 resourcesGetting Started guide, Supported Providers
prompts2 prompts with completionsgovernance_audit, policy_preflight
logginglogging/setLevel8 levels, per-session, audit trail
completionscompletion/completeworkspace (auth-scoped), provider, model (provider-aware)

Ecosystem

This repo is part of the ThinkNEO ecosystem:

ProjectDescription
ThinkNEO PlatformEnterprise AI governance platform
AIRGPAI Runtime Governance Protocol — open standard
A2ASTCA2A Security & Trust Conformance
ThinkNEO SMB HubBusiness applications for SMBs
Robotics GovernanceRobot fleet governance dashboard

Security

See SECURITY.md for vulnerability reporting.

Contributing

See CONTRIBUTING.md.

Related

ServerDescriptionTools
thinkneo-control-planeEnterprise AI Control Plane (this repo)72 tools
thinkneo-mcp-smb-productsSMB standalone products — self-serve via TNC credits37 tools

License

Apache-2.0 — see LICENSE.

About

ThinkNEO AI Technology Co., Ltd. — Hong Kong CR No. 2296774.

Built by the team behind the ThinkNEO Enterprise AI Control Plane, AIRGP protocol, and A2ASTC conformance suite.

NVIDIA Inception | Anthropic Partner | Linux Foundation A2A

來源：README.md，提交 0f014e1

工具

0
SourceWeft 尚未讀取此伺服器的工具。

版本歷史

1
  1. v1.29.0最新Sep 16, 2026

評分

已滿足適用檢查項的 50%

該評分衡量此收錄條目的完整程度，依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價，也不表示伺服器安全或目前可用：可連通性是帶日期的檢查結果，評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分

    請保持端點能夠回應 MCP 握手；SourceWeft 每 30 天探測一次。

  • 已宣告認證方式必需10 分

    請在註冊中心條目中宣告憑證請求標頭，或保持端點能夠回應探測，以便判定其認證方式。

  • 已列出工具15 分

    請讓伺服器在無憑證時回應 tools/list，或發布可在沙箱中無憑證啟動的軟體包。

  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分