About Simbrief Mcp Server
A Python MCP server that lets Claude Desktop retrieve SimBrief flight-plan data through tools for flight details, weather, fuel, and more. It uses a SimBrief Pilot ID and can fetch the latest dispatch when no plan_id is supplied.
Key features
- 0114 tools for SimBrief flight plans
- 02Weather, NOTAM, and route details
- 03Fuel, weight, and timing data
- 04Latest-plan retrieval without plan_id
- 05Optional complete flight-plan JSON
Use cases
- 01Review weather and NOTAMs for a planned flight
- 02Inspect fuel, weight, and timing figures
- 03Retrieve an ATC flight-plan string
- 04Compare fuel and time effects of altitude changes
MCP support
Exposes SimBrief flight-plan data through MCP tools for clients such as Claude Desktop. The server requires SIMBRIEF_PILOT_ID.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMESimBrief MCP Server
A Model Context Protocol server that gives Claude Desktop direct access to your SimBrief flight plans — no Cloudflare, no OAuth, no infrastructure required.
Features
14 tools covering every section of a SimBrief OFP:
| Tool | Description |
|---|---|
get_flight_summary | Flight number, aircraft, route, distance, cruise, ETE, fuel |
get_weather | METAR, TAF and ATIS for departure, arrival and alternate |
get_fuel_plan | Full fuel breakdown: taxi, trip, contingency, alternate, reserve, extra |
get_weights | OEW, payload, ZFW, TOW, ramp weight, landing weight |
get_times | Scheduled OUT/OFF/ON/IN, ETE, block time, taxi, endurance |
get_atc_flightplan | ATC flight plan string ready for filing |
get_aircraft_info | Type, registration, engines, equipment codes |
get_navlog | Full waypoint list with altitude, distance and fuel per leg |
get_notams | All NOTAMs (departure, arrival, en-route) |
get_alternate_info | Alternate airport details and navlog |
get_performance | Takeoff & landing performance (TLR), if available |
get_crew | Captain, first officer, dispatcher, purser, flight attendants |
get_impacts | Fuel and time sensitivity to altitude and cost index changes |
get_full_flight_plan | Complete raw JSON for custom analysis |
All tools accept an optional plan_id parameter — leave it empty to always fetch your latest dispatch.
Requirements
Installation
git clone https://github.com/Emanuele94/SimBrief-MCPServer.git
cd SimBrief-MCPServer
uv sync
Configuration
Your SimBrief Pilot ID is passed via an environment variable in the MCP config — no code changes needed.
Find your Pilot ID under SimBrief → Account Settings → Pilot ID.
Claude Desktop integration
Add the following to your claude_desktop_config.json:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"simbrief": {
"command": "uv",
"args": [
"run",
"--project", "/absolute/path/to/SimBrief-MCPServer",
"python",
"/absolute/path/to/SimBrief-MCPServer/server.py"
],
"env": {
"SIMBRIEF_PILOT_ID": "your_pilot_id_here"
}
}
}
}
Then restart Claude Desktop. The SimBrief tools will appear automatically.
The server will refuse to start with a clear error message if
SIMBRIEF_PILOT_IDis not set.
Usage examples
Once connected, you can ask Claude things like:
- "What's my latest flight plan?"
- "Show me the weather for my next flight."
- "How much fuel do I have planned and what's the breakdown?"
- "Give me the full ATC flight plan string."
- "What happens to fuel burn if I fly 2000 ft lower?"
- "Show me the first 20 waypoints of my navlog."
Development
Install dev dependencies:
uv sync --all-extras
Run tests:
uv run pytest -v
Lint and format:
uv run ruff check .
uv run ruff format .
All tests run fully offline — the SimBrief API is mocked so no internet connection or real Pilot ID is required.
Contributing
- Fork the repository
- Create a feature branch (
git checkout -b feature/my-feature) - Make your changes and add tests
- Ensure the CI pipeline passes locally (
uv run pytest && uv run ruff check .) - Open a Pull Request against
main
PRs must pass all checks (tests + lint) before they can be merged.
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.