Back to Apps

tinyMCP
Supports UIby golioth
Control embedded devices and hardware via the Model Context Protocol using Golioth management API.
0 stars
Works in:Gemini CLI
Exposes:Tools
What it does\ntinyMCP allows LLMs to interact with embedded devices by bridging the Model Context Protocol with the Golioth platform. It exposes device functionality, such as LED control or sensor readings, as MCP tools that an AI can invoke to manage physical hardware remotely.\n\n## Tools\n- RPC Tooling: Dynamically exposes Remote Procedure Calls (RPCs) defined in the Golioth LightDB State as MCP tools.\n- Device Management: Enables interaction with remote devices via the Golioth management API.\n\n## Installation\nAdd the following to your claude_desktop_config.json (ensure the server is running locally):\n\njson\n{\n \"mcpServers\": {\n \"tinymcp\": {\n \"command\": \"go run ./server\",\n \"args\": [],\n \"env\": {\n \"TINYMCP_PROJECT\": \"your-project-id\",\n \"TINYMCP_DEVICE\": \"your-device-id\",\n \"TINYMCP_API_KEY\": \"your-api-key\"\n }\n }\n }\n}\n\n\n## Supported hosts\n- Claude Desktop\n- Claude Code\n- Gemini CLI\n- MCP Inspector
Quick install
go run ./serverInformation
- Pricing
- free
- Published
- 4/17/2026
- stars
- 0
Categories
Choose your AI client and follow the steps below.
Gemini CLI
Configure in .gemini/settings.jsonClaude Desktop
Configure with TINYMCP_PROJECT, TINYMCP_DEVICE, and TINYMCP_API_KEY env vars.





