An MCP server that lets AI agents launch the Godot editor, run projects, capture debug output, and manage scenes.
ThingsPanel/thingspanel-mcp
An MCP server that lets AI assistants like Claude and GPT query and control devices on the ThingsPanel IoT platform and ThingsVis dashboards.
- Stars
- 48
- Forks
- 23
- Open issues
- 2
- Last commit
- 14 days ago
What is it?
ThingsPanel MCP is a Python server that exposes ThingsPanel and ThingsVis APIs as Model Context Protocol tools, so MCP-compatible assistants can work with IoT data and devices in natural language. It provides 378 tools in total: 14 focused tools for devices, telemetry, dashboards and commands, plus 364 individually named tools generated from an allow-listed API manifest covering 312 ThingsPanel and 52 ThingsVis operations.
Each generated tool maps to one fixed HTTP method and route, and callers supply path parameters, query, JSON body or a file to upload. Write and control operations require an explicit confirmed=true flag, and results are returned as structured JSON with business-code error detection. Credentials are managed through named profiles in a local config file or environment variables, and authorization is always enforced by the connected service.
The server runs over stdio by default, with SSE optional, and installs from PyPI or source. Setup guides are included for Codex, Claude Desktop and WorkBuddy.
Key features
- 01Exposes 378 MCP tools covering devices, telemetry, alarms, dashboards, products and uploads.
- 02Generated tools map to fixed, allow-listed API routes rather than arbitrary URLs.
- 03Write and control operations require confirmed=true before they are sent.
- 04Named credential profiles let you use different ThingsPanel or ThingsVis identities.
- 05Returns structured JSON results and checks ThingsPanel business codes.
Use cases
- Letting an AI assistant look up device status and recent telemetry on a ThingsPanel instance.
- Querying alarms or device groups through natural-language requests.
- Sending commands to devices with an approval step before execution.
- Automating dashboard lookups in ThingsVis from an MCP-enabled client.
Topics
FAQ
- What is thingspanel-mcp?
- An MCP server that lets AI assistants like Claude and GPT query and control devices on the ThingsPanel IoT platform and ThingsVis dashboards. ThingsPanel MCP is a Python server that exposes ThingsPanel and ThingsVis APIs as Model Context Protocol tools, so MCP-compatible assistants can work with IoT data and devices in natural language. It provides 378 tools in total: 14 focused tools for devices, telemetry, dashboards and commands, plus 364 individually named tools generated from an allow-listed API manifest covering 312 ThingsPanel and 52 ThingsVis operations.
- Is thingspanel-mcp free to use? What license does it have?
- thingspanel-mcp is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
- Is thingspanel-mcp still maintained?
- Actively maintained. The last commit to thingspanel-mcp was on Oct 8, 2026.
- What can I use thingspanel-mcp for?
- Letting an AI assistant look up device status and recent telemetry on a ThingsPanel instance. Querying alarms or device groups through natural-language requests. Sending commands to devices with an approval step before execution. Automating dashboard lookups in ThingsVis from an MCP-enabled client.
- Where can I get thingspanel-mcp?
- The source code and installation instructions are on GitHub: https://github.com/ThingsPanel/thingspanel-mcp
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Unity Editor and runtime plugin and MCP server that lets AI agents like Claude, Cursor and Copilot operate Unity projects and run LLMs inside games.
A Model Context Protocol (MCP) plugin that lets AI coding assistants like Cursor, Claude Code and Codex control and query the Unity Editor.
Open-source memory layer that captures coding agent session history across Claude Code, Cursor, Codex and 20+ other harnesses, and turns it into reusable knowledge.
A Python framework for building MCP servers, clients, and interactive apps that connect LLMs to tools and data.
Official Python SDK for building Model Context Protocol servers and clients that connect LLM applications to tools, data and prompts.