INDI MCP Server
The INDI MCP Server lets you control astrophotography equipment and manage an INDI server via the Model Context Protocol (MCP).
INDI Server Management
Start the INDI server (
indiserver) on a specified port (default: 7624)Stop, restart, and check the running status and port of the INDI server
Driver Management
List all installed drivers from the INDI catalog (name, label, version, family, binary, install status)
Start a driver by its catalog label (e.g.
"CCD Simulator")Stop a running driver by its catalog label
List all currently running drivers
INDI Event Monitoring / Messaging
Start/stop streaming INDI property and message events from the server
Check whether the event stream is active and on which host/port
Retrieve recent INDI events (newest first), optionally filtered by device name
Equipment Control
Send property commands to connected INDI devices — set named elements on a device's property to control mounts, cameras, filter wheels, focusers, and other astrophotography gear
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@INDI MCP Server Connect to the ASI1600MM camera and set exposure to 30 seconds."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
INDI MCP Server
An MCP server that controls astrophotography equipment via INDI on a Raspberry Pi (or equivalent device), and exposes it to other computers on the local network.
What it does
Equipment control — connect to an INDI server and control mounts, cameras, filter wheels, focusers and other astrophotography gear through MCP tools.
INDI server management — manage the INDI server itself: install/remove drivers, and start, stop or restart the server, all via MCP.
Frame storage — captured frames are stored on the Raspberry Pi and can be listed, inspected and transferred to another computer on the local network via MCP.
Related MCP server: mcp-server-ascom
Documentation
Deployment — running the server locally (
stdio) vs. as a systemd service on the Raspberry Pi (streamable-http)Rig YAML Schema — field reference for
rigs/*.yamlimaging rig definitionsObservatory Location YAML Schema — field reference for
observatories/*.yamllocation definitionsScript YAML Schema — field reference for the YAML scripting layer; built-in primitive/composed scripts ship under
scripts/Property/Message JSON Payload Schema — field reference for the
kind/type-tagged JSON carried inside MCP tool results and event streams
Debug CLI
indi-mcp-cli is a small standalone tool for manually testing/debugging the INDI server and
driver management tools, without needing an MCP client:
uv run indi-mcp-cli server status
uv run indi-mcp-cli server start --port 7624
uv run indi-mcp-cli driver list
uv run indi-mcp-cli driver start "CCD Simulator"
uv run indi-mcp-cli listen --device "CCD Simulator" # prints incoming events until Ctrl+CThe driver catalog is read from /usr/share/indi/ by default, which only exists where INDI's
drivers are actually installed (e.g. the Raspberry Pi). On a machine with a local INDI install
elsewhere (e.g. Homebrew on macOS, typically /usr/local/share/indi or
/opt/homebrew/share/indi), point the server at it via INDI_MCP_DRIVER_CATALOG_DIR
(INDIMCP-128) — this applies to the MCP server itself, not just indi-mcp-cli's driver
subcommands, since both read the same catalog:
export INDI_MCP_DRIVER_CATALOG_DIR=/usr/local/share/indi
uv run indi-mcp-cli driver listStatus
Early setup stage — MCP server skeleton in place, with INDI server management tools (start/stop/restart/status) implemented.
Tech stack
Python 3.12+, managed with uv
Official Python MCP SDK (
mcp)indipyclient— pure-Python INDI client, used for equipment controlindiweb— used as a library only (itsIndiServer/DriverCollectionclasses), forindiserverprocess/FIFO control and driver-catalog parsing; its bundled web app is not usedastropy— celestial-geometry computation (Sun/Moon position, illumination) forcapture_frame's FITS header enrichment, see docs/FitsHeaders.mdRuff for linting and formatting
ty for static type checking
pytest, with
pytest-asyncioandpytest-covpre-commit to run the above on every commit
Development setup
uv sync --dev
uv run pre-commit installCommon tasks:
uv run ruff check . # lint
uv run ruff format . # format
uv run ty check . # type-check
uv run pytest --cov # testContributing / branching model
This project follows a git-flow-style workflow:
main— always releasable; only accepts merges fromrelease/*orhotfix/*branches.develop— integration branch for ongoing work.feature/*— branched from and merged back intodevelop.
A CI check (enforce-merge-policy) rejects pull requests that don't follow these rules.
Available Tools
13 toolsget_indi_messaging_statusA
Report whether the INDI messaging stream is running, and its host/port.
Inputs: no named parameters. Returns: host, port, running
get_indi_server_statusA
Report whether the INDI server (indiserver) is running, and on which port.
Inputs: no named parameters. Returns: port, running
list_indi_driver_catalogA
List every INDI driver installed on this device, whether or not it is running.
Inputs: no named parameters. Returns: result
list_indi_messagesC
List the most recently seen INDI events, newest first, optionally filtered to one device.
Inputs: limit, device. Returns: result
list_running_indi_driversA
List all currently running INDI drivers.
Inputs: no named parameters. Returns: result
restart_indi_serverA
Restart the INDI server (indiserver), optionally switching to a new port.
Inputs: port. Returns: port, running
send_indi_propertyC
Send a command to an INDI device, setting elements on its property name.
Inputs: name (required), device (required), elements (required). Returns: kind, name, type, state, +4 more
start_indi_driverB
Start the INDI driver identified by its catalog label (e.g. "CCD Simulator").
Inputs: label (required). Returns: label, running
start_indi_messagingA
Connect to the INDI server and start streaming its property/message events.
Inputs: host, port. Returns: host, port, running
start_indi_serverB
Start the INDI server (indiserver) on the given port.
Restarts it if it is already running.
Inputs: port. Returns: port, running
stop_indi_driverB
Stop the running INDI driver identified by its catalog label.
Inputs: label (required). Returns: label, running
stop_indi_messagingA
Disconnect from the INDI server and stop streaming its events.
Inputs: no named parameters. Returns: host, port, running
stop_indi_serverA
Stop the running INDI server (indiserver).
Inputs: no named parameters. Returns: port, running
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 13 tools
Every tool targets a distinct operation: server control, driver management, messaging, listing, and property sending. No overlap in functionality.
All tool names follow a consistent verb_noun pattern with snake_case, e.g., start_indi_server, list_indi_driver_catalog, send_indi_property.
13 tools provide complete coverage for managing an INDI server and its drivers without being excessive; each tool serves a clear purpose.
Covers all major operations: server lifecycle, driver start/stop, messaging, and property setting. Minor gap: no dedicated tool to query a driver's current property state, though messages provide partial coverage.
Maintenance
Related MCP Connectors
Hosted MCP server for task-first delegation to remote workstations and workers.
Real-time planetary signal engine and Model Context Protocol (MCP) server for autonomous AI agents.
QuLab MCP remote server (Streamable HTTP) for computational science and lab tools.
Documentation for the Spektralwerk spectrometer SCPI API as a streamable HTTP MCP Server
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceA protocol server enabling AI agents to control astrophotography equipment through the N.I.N.A. (Nighttime Imaging 'N' Astronomy) software, allowing for natural language command processing of cameras, mounts, focusers, and other astronomy equipment.14MIT
- AlicenseNot gradedqualityCmaintenanceControl telescopes, cameras, and focusers with AI through natural language, using any ASCOM Alpaca device.MIT
- FlicenseAqualityDmaintenanceEnables AI agents to control N.I.N.A. astronomy software remotely, including mount, camera, sequencer, and other equipment via the ninaAPI plugin.66-
- AlicenseNot gradedqualityDmaintenanceMCP 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.MIT