Aerospace

You can run an MCP server that exposes both HTTP API endpoints and a Model Context Protocol interface for intelligent control and automation in aerospace flight planning and orbital dynamics. This server provides fast, in-memory data access, geometry and atmosphere models, and modular tools that let you plan flights, compute routes, evaluate performance, and explore orbital trajectories. Use it with MCP clients to automate workflows, integrate AI agents, and prototype advanced aerospace analyses.

How to use

Connect to the MCP server using an MCP client to execute flight planning, airport searches, and orbital calculations. You will interact through either the HTTP API or the MCP interface, depending on your client setup. Use the HTTP path for standard REST-based requests to generate flight plans, search airports, and query performance data. Use the MCP interface to call specialized tools for tasks such as orbital propagation, trajectory optimization, and propulsion analyses. You can run multiple requests in sequence or in parallel to accelerate experimentation and validation.

How to install

Prerequisites: you need Python 3.11 or newer, and a suitable runtime for your chosen installation path. If you prefer a quick setup with a package manager, you can follow the provided installation options. Otherwise, you can build and run a container image.

# Option A: UV Package Manager (Recommended)
curl -LsSf https://astral.sh/uv/install.sh | sh

# Clone the project and enter the directory
git clone https://github.com/username/aerospace-mcp.git
cd aerospace-mcp

# Create and activate virtual environment
uv venv
source .venv/bin/activate  # Linux/macOS
# .venv\Scripts\activate     # Windows

# Install core/runtime dependencies
uv add fastapi uvicorn[standard] airportsdata geographiclib pydantic python-dotenv
uv add openap
uv add mcp

# Install optional aerospace analysis dependencies as needed
uv add --optional-dependencies atmosphere
uv add --optional-dependencies space
uv add --optional-dependencies all

# Verify installation
python -c "import main; print('✅ Installation successful')"
``n
```bash
# Option B: Pip (Traditional)

# Clone repository
git clone https://github.com/username/aerospace-mcp.git
cd aerospace-mcp

# Create virtual environment
python -m venv .venv
source .venv/bin/activate  # Linux/macOS
# .venv\Scripts\activate     # Windows

# Upgrade pip
pip install --upgrade pip

# Install core dependencies
pip install fastapi uvicorn[standard] airportsdata geographiclib pydantic python-dotenv

# Install optional dependencies when needed
pip install openap
pip install mcp
pip install python-dotenv

# Install from project metadata
pip install -e .

# Verify installation
python -c "import main; print('✅ Installation successful')"
```"} ,{

Additional sections

Configuration and runtime flags are designed to be straightforward. The server loads environment variables from a local file named .env and supports both HTTP and MCP interfaces. You can switch between modes by setting AEROSPACE_MCP_MODE to http or mcp, choose host and port for the HTTP interface, and enable AI-assisted tools with LLM_TOOLS_ENABLED.

Security and safe usage are important. This software is intended for educational and research purposes and is not suitable for real-world aviation navigation. Do not rely on it for operational decisions. Keep API keys and access tokens secure, and limit exposure of the HTTP endpoint in public networks.

Examples demonstrate typical workflows including basic flight planning, airport searches, and orbital calculations. You can adapt these patterns to your own experiments, integrating them with automation pipelines, CI workflows, or AI agents that leverage MCP tool calls.

If you run into issues during installation or usage, verify Python versions, ensure required system libraries (such as GeographicLib dependencies) are installed, and check that the chosen entry points are executable in your environment. For development testing, you can run the server with live reloading and inspect logs to diagnose problems quickly.

HTTP and MCP server configurations (examples)

The following configurations illustrate how you can connect clients to the MCP server and how to expose an MCP interface locally or remotely.

{
  "type": "http",
  "name": "aerospace_mcp_http",
  "url": "https://mcp.example.com/mcp",
  "args": []
}

{
  "type": "stdio",
  "name": "aerospace_mcp_cli",
  "command": "python",
  "args": ["-m", "aerospace_mcp.server"],
  "cwd": "/path/to/aerospace-mcp",
  "env": [
    {"name": "PYTHONPATH", "value": "/path/to/aerospace-mcp"}
  ]
}

Notes

• The HTTP config provides a remote MCP endpoint you can register with your MCP client. - The stdio config runs the local MCP server directly and is suitable for development or testing inside a local environment. - Ensure environment variables are set appropriately in your deployment to control host, port, log level, and tool availability.

Available tools

search_airports

Find airports by IATA code or city name across a global database

plan_flight

Generate a complete flight plan including route and performance estimates

calculate_distance

Compute great-circle distance between two points with optional route stepping

get_aircraft_performance

Provide performance estimates for a given aircraft and distance

get_atmosphere_profile

Return ISA atmosphere profiles for specified altitudes

wind_model_simple

Calculate wind profiles using simple models

transform_frames

Transform coordinates between geodetic, ECEF, and ECI frames

geodetic_to_ecef

Convert latitude/longitude/altitude to ECEF coordinates

ecef_to_geodetic

Convert ECEF coordinates to geodetic latitude/longitude/altitude

wing_vlm_analysis

Analyze wing aerodynamics using vortex lattice methods

airfoil_polar_analysis

Generate airfoil polars across angles of attack and Reynolds numbers

calculate_stability_derivatives

Compute stability derivatives for a given geometry

propeller_bemt_analysis

Assess propeller performance using blade element momentum theory

uav_energy_estimate

Estimate UAV endurance and energy consumption

get_airfoil_database

Fetch available airfoil coefficients

get_propeller_database

Fetch available propeller data

rocket_3dof_trajectory

Simulate 3DOF rocket trajectory with atmosphere integration

estimate_rocket_sizing

Size a rocket for mission requirements

optimize_launch_angle

Optimize launch angle for mission objectives

optimize_thrust_profile

Optimize thrust profiles for trajectory goals

trajectory_sensitivity_analysis

Analyze parameter sensitivity for trajectory design

get_system_status

Query system health and capabilities

elements_to_state_vector

Convert orbital elements to state vector

state_vector_to_elements

Convert state vector to orbital elements

propagate_orbit_j2

Propagate orbit with J2 perturbations

calculate_ground_track

Compute satellite ground track from orbital states

hohmann_transfer

Calculate Hohmann transfer orbit

orbital_rendezvous_planning

Plan orbital rendezvous maneuvers

genetic_algorithm_optimization

Trajectory optimization using GA

particle_swarm_optimization

Trajectory optimization using PSO

monte_carlo_uncertainty_analysis

Monte Carlo analysis of trajectory uncertainty

porkchop_plot_analysis

Generate porkchop plots for interplanetary transfers

optimize_launch_strategy

Optimize launch parameters for missions