Ignition Doc MCP
An MCP server that provides AI assistants with real-time access to Inductive Automation Ignition documentation, enabling accurate answers on Ignition-specific topics by searching live docs and fetching full pages.
README
Ignition Doc MCP
Ground your AI answers in live Inductive Automation Ignition documentation.
What it does
Ignition Doc MCP is a Model Context Protocol (MCP) server that gives AI assistants like Claude direct access to the official Inductive Automation Ignition documentation. Instead of relying on training data that may be outdated or incorrect, the AI fetches real answers from live docs — eliminating hallucination on Ignition-specific topics.
Covers both the Ignition User Manual (always the latest version) and the Ignition SDK Programmer's Guide.
How it works
The server queries the Typesense search backends that power docs.inductiveautomation.com and sdk-docs.inductiveautomation.com in real time. No API key required, no local doc files, no indexing step — every search goes directly to Inductive Automation's search backend and returns content that is always up to date.
The User Manual search is pinned to the docs-default-current tag, which automatically resolves to the latest published version — no manual version bumps needed when Ignition releases a new version.
Prerequisites
-
Python 3.11 or later — python.org/downloads
-
uv — fast Python package manager
curl -LsSf https://astral.sh/uv/install.sh | sh -
Claude Code CLI — installation guide
Installation
1. Clone the repository
git clone https://github.com/nurnaufal321/inductiveautomation-doc-mcp.git
cd inductiveautomation-doc-mcp
2. Install dependencies
uv sync
3. Register with Claude Code
claude mcp add ignition-docs --scope user -- uv run --directory /path/to/inductiveautomation-doc-mcp python server.py
Replace /path/to/inductiveautomation-doc-mcp with the absolute path to the cloned folder.
4. Restart Claude Code to pick up the new MCP server. You should see ignition-docs listed when you run:
claude mcp list
Available Tools
Once registered, Claude has access to three tools:
| Tool | Description |
|---|---|
search_ignition_docs |
Search the Ignition User Manual (latest version) by keyword. Optional: n_results (default 5, max 20). |
search_ignition_sdk |
Search the Ignition SDK Programmer's Guide by keyword. Optional: n_results (default 5, max 20). |
get_page |
Fetch the full text of a documentation page by URL. Optional: max_chars (default 4000, max 12000). |
Usage Examples
Ask Claude questions like:
- "How do I configure an OPC-UA connection in Ignition?"
- "What Vision window types are available?"
- "How does tag history deadband work?"
- "How do I create a GatewayModuleHook for my Ignition module?"
- "What are the core modules included in Ignition?"
Claude will search the live docs and cite the exact page it used.
Scope
Ignition User Manual
Covers the full Ignition platform including:
- Tags, Tag Historian, and Tag Diagnostics
- Perspective and Vision modules
- Scripting and Python in Ignition
- Alarm Notification and Event Streams
- OPC-UA, SQL Bridge, Reporting
- Gateway, Designer, and Client configuration
- Transaction Groups and Database connections
Ignition SDK Programmer's Guide
Covers module development including:
GatewayModuleHook,DesignerModuleHook,ClientModuleHook- Tag providers, drivers, and OPC server development
- Gateway network communication
- Component and style development
References
- Ignition User Manual
- Ignition SDK Programmer's Guide
- Model Context Protocol
- MCP Python SDK
- uv — Python package manager
- Claude Code
Disclaimer
This project is not affiliated with, endorsed by, or supported by Inductive Automation. It queries Inductive Automation's publicly accessible documentation search backend for personal and developer use. Users are responsible for complying with Inductive Automation's terms of use.
License
This project is licensed under the MIT License. See LICENSE for details.
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。