indigo-mcp
MCP server for the INDIGO astronomy automation protocol, enabling AI agents to control telescopes, cameras, focusers, filter wheels, domes, and other observatory equipment through natural language.
README
indigo-mcp
MCP (Model Context Protocol) server for INDIGO astronomy automation protocol.
Lets AI agents (Claude, Hermes, etc.) control telescopes, cameras, focusers, filter wheels, domes, and other astronomical equipment through the INDIGO protocol.
Architecture
AI Agent ←→ MCP Protocol ←→ indigo-mcp ←→ INDIGO Server (port 7624) ←→ Hardware
Quick Start
# Install
pip install -e ".[dev]"
# Run (connects to INDIGO at localhost:7624)
indigo-mcp
# Or specify host/port
indigo-mcp --host 192.168.1.100 --port 7624
Configuration
Environment variables:
INDIGO_HOST— INDIGO server host (default:localhost)INDIGO_PORT— INDIGO server port (default:7624)INDIGO_WS— Use WebSocket transport instead of raw TCP (default:false)
Or pass as CLI arguments:
indigo-mcp --host 192.168.1.100 --port 7624 --ws
MCP Tools
| Tool | Description |
|---|---|
indigo_list_devices |
List all connected devices and their interfaces |
indigo_get_property |
Get current value of a device property |
indigo_set_property |
Set a device property value |
indigo_connect_device |
Connect to a device |
indigo_disconnect_device |
Disconnect from a device |
indigo_capture_image |
Take an exposure with a CCD |
indigo_abort_exposure |
Abort an ongoing exposure |
indigo_slew |
Slew telescope to RA/Dec coordinates |
indigo_park |
Park the telescope |
indigo_get_coordinates |
Get current telescope coordinates |
indigo_set_tracking |
Enable/disable mount tracking |
indigo_move_focuser |
Move focuser by relative steps |
indigo_set_filter |
Set filter wheel slot |
indigo_script_upload |
Upload & persist a JavaScript script to the Scripting Agent |
indigo_script_list |
List scripts stored on the Scripting Agent |
indigo_script_execute |
Execute a stored script by name (waits for Busy→Ok/Alert) |
indigo_script_run |
Run an inline JS snippet (e.g. launch a Sequencer.js sequence) |
indigo_script_delete |
Delete a stored script |
indigo_script_monitor |
Monitor script execution: state changes, log messages, watched properties |
Project Structure
indigo-mcp/
├── pyproject.toml
├── README.md
├── src/
│ └── indigo_mcp/
│ ├── __init__.py
│ ├── server.py # MCP server entry point
│ ├── client.py # INDIGO TCP/WS client
│ ├── protocol.py # JSON message serialization/deserialization
│ └── tools.py # MCP tool implementations
└── tests/
└── __init__.py
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.