
Cognigy Ai Mcp Management Server
io.github.TsvetanG2由 GitHub 帳號 TsvetanG2 發布v0.2.1更新於 Oct 24, 2026
MCP server for Cognigy.AI - 132 tools to build, configure & operate conversational AI agents
概覽
本機 MCP 伺服器,透過 132 個 Management API 工具讓助理建置、設定、測試與營運 Cognigy.AI 對話式 AI 代理。
- 可以做什麼
- 管理專案、流程、節點、意圖與 NLU 訓練,包含評分與稽核檢查。執行 playbook 與回歸測試,注入或重設工作階段內容。建立、還原、比對與提升快照,建立、合併、上傳或下載套件。設定 LLM、NLU 連接器、Knowledge AI 存放區與來源、函式與擴充功能。處理聯絡人檔案、分析、稽核記錄、真人客服轉接與組織層級搜尋。追蹤長時間執行的非同步工作,並將清單結果分頁。
- 適用情境
- 適合在 Cognigy.AI 上開發的開發者、解決方案架構師與合作夥伴,希望用 AI 助理取代 Cognigy 介面來以指令碼修改代理、執行 NLU 訓練與回歸測試,或在環境間提升快照與套件。
- 執行需求
- 需要 Node.js 20 或更高版本,並另行安裝 @cognigy/rest-api-client 同儕相依套件。需要具備 API 存取權的 Cognigy.AI 帳戶(試用、SaaS 或地端部署)。必須設定環境變數 COGNIGY_BASE_URL 與 COGNIGY_API_KEY,COGNIGY_DEFAULT_PROJECT_ID 為選用。需要能連線至 Cognigy API 端點的網路。
安裝
在 SourceWeft 中
- 開啟 儀表板中的 Cognigy Ai Mcp Management Server,將其新增到工作區。
- 為需要使用其工具的對話啟用該服務。
Desktop only,透過 STDIO。 STDIO 服務會啟動本機處理程序,因此需要 SourceWeft 桌面主機。
其他 MCP 客戶端
參照 儲存庫 中的啟動說明。
README
Cognigy.AI Management MCP Server
[CI] [npm version] [npm downloads] [node] [License: MIT] [Glama Score] [MCP Registry] [MCP Badge]
[cognigy-ai-mcp-management-server]
Model Context Protocol server for managing Cognigy.AI virtual agents through the Management API
This is an independent, open-source MCP server and is not affiliated with, endorsed by, or sponsored by Cognigy or NiCE. It requires your own valid Cognigy.AI account and API key, used in accordance with Cognigy's commercial license terms. "Cognigy" and "Cognigy.AI" are trademarks of their respective owners.
What is this?
cognigy-ai-mcp-management-server is a local MCP server that enables AI coding assistants (Claude, Cursor, etc.) to build, configure, test, and operate Cognigy.AI conversational AI agents programmatically.
Instead of clicking through the Cognigy UI, you can now:
- Create and manage flows, nodes, and intents via natural language
- Run NLU training and regression tests automatically
- Deploy snapshots and packages across environments
- Configure LLMs, Knowledge AI, and integrations
Built for: Developers, solution architects, and SI partners who build on Cognigy.AI.
Requirements
- Node.js 20.0.0 or higher
- Cognigy.AI account with API access (Trial, SaaS, or on-premises)
- API Key generated from Cognigy UI (My Profile → API Keys)
Installation
Important: The @cognigy/rest-api-client package is licensed under "Cognigy Proprietary License". By installing it, you agree to Cognigy's license terms.
Configuration
Set environment variables before running:
Common Base URLs:
MCP Client Configuration
Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
Claude Code
Add to .mcp.json in your project root:
Cursor
Add to .cursor/mcp.json:
Available Tools
This server provides 132 MCP tools organized by domain:
Key Features
- Safe by default: All mutating tools use
dryRun: trueby default - Async-aware: Long-running operations poll until completion
- Security: API keys only in memory, secrets automatically redacted
- Pagination: All list operations support
limitandskip
Development & Testing
Live API Testing
Build
Regenerate Types (optional)
If you need to update the generated types from a newer Cognigy API:
Important: Dependencies
This package requires @cognigy/rest-api-client as a peer dependency. This means:
- You must install it separately (see Installation above)
- You accept Cognigy's license terms by installing their package
- We do not bundle or redistribute any Cognigy code
You are responsible for:
- Reviewing and accepting Cognigy's proprietary license terms
- Having appropriate rights to use the Cognigy API
- Keeping your API credentials secure
The Cognigy REST API client is the official SDK maintained by Cognigy GmbH and is published on npm under "Cognigy Proprietary License".
License
This MCP server is released under the MIT License. See LICENSE for details.
Note: The MIT license applies only to this MCP server code. Dependencies (particularly @cognigy/rest-api-client) are subject to their own licenses.
Contributing
Contributions are welcome! Please:
- Fork the repository
- Create a feature branch (
git checkout -b feature/amazing-feature) - Follow existing code patterns (Zod schemas, dryRun flags, etc.)
- Add tests for new tools
- Run
npm test && npm run buildbefore committing - Submit a Pull Request
Development Guidelines
- All tools must have Zod input validation
- Mutating tools must support
dryRunflag (default: true) - Tool descriptions should be LLM-friendly (1-2 sentences)
- Never log or expose API keys/secrets
- Test against mock server before live API
Support
- Issues: GitHub Issues
- Cognigy Docs: docs.cognigy.com
- MCP Spec: modelcontextprotocol.io
Built with Model Context Protocol SDK
來源:README.md,提交 e647397
工具
0版本歷史
3- v0.2.1最新Oct 5, 2026
- v0.2.0Oct 4, 2026
- v0.1.4Sep 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