Simulate electric UAV powertrains and search a public motor, propeller and battery database.
Scored across 7 tools
Each tool has a clearly distinct role: search_components vs get_component (find vs read-one), estimate_propeller (single prop closed-form) vs simulate_powertrain (whole powertrain operating point) vs sweep_powertrain (range), plus get_result and get_validation_summary for retrieval/accuracy. The overlapping-sounding propeller tools are distinguished by scope and model in their descriptions.
All seven tools follow a predictable snake_case verb_noun pattern (estimate_propeller, get_component, get_result, get_validation_summary, search_components, simulate_powertrain, sweep_powertrain). The get_/search_/simulate_/sweep_ prefixes are used consistently.
Seven tools is well-scoped for a propulsion simulation service, covering estimation, simulation, sweep, component lookup, result retrieval and validation without redundancy or bloat. Each tool earns its place.
The surface covers the core lifecycle: find components, read one, estimate, simulate, sweep, retrieve results, and check model accuracy. Minor gaps exist (e.g. no direct comparison of multiple setups or component-creation tools), but core agent workflows are covered.
Thrust, torque and shaft power for one propeller, from its printed size.
A closed-form momentum plus blade-element equation — no motor, no battery,
no account. Give the size as it is printed: a 10x5 is `diameter_in=10`,
`pitch_in=5`. `chord_ratio` is the chord at 75 % radius over the diameter:
0.065 thin electric, 0.07 sport, 0.10 slow flyer, 0.11 multirotor.
Inputs: rpm (required), pitch_in (required), diameter_in (required), blades, +4 more. Returns: object
Read one database row by its id (comp_…), with provenance.
Propeller rows give diameter, pitch, blade count, weight and maximum rpm.
Blade station geometry is never returned.
Inputs: component_id (required). Returns: object
Read a stored result: a share token from a run, or a simulation_id.
`simulation_id` needs a ThrustLab API key in `Authorization: Bearer` and
reads only that account's own runs.
Inputs: token, simulation_id. Returns: object
How accurate a model is, measured against wind-tunnel and bench data.
`model` is "fast", "full", or an exact report slug such as "prom-5.3". The
numbers are error against measured data by partition and channel, with the
envelope they were measured inside. Quote the model name with the number.
Inputs: model. Returns: object
Find motors, propellers or batteries in the ThrustLab database.
component_type is "motor", "propeller" or "battery". query is a
case-insensitive substring of the part name or its maker ("APC", "T-Motor",
"13x6.5"). The maker sits under spec.brand for motors and batteries and under
spec.type for propellers. limit is capped at 200 rows a
page; when has_more is true, pass the returned next_offset as offset to
read the next page. Each row carries its datasheet values, its source and the
CC BY 4.0 attribution line. Pass a returned id to
simulate_powertrain.
Inputs: component_type (required), limit, query, offset, +2 more. Returns: object
Solve one operating point of a whole powertrain on the Fast model.
Battery, ESC, motor and propeller are solved together, so the answer is a
real thrust and current, not a propeller curve. The numbers come back in
`result` (`result.All` = system totals in SI units: thrust N, current A,
power W, time s; one entry per rotor; `result.Battery`), with a share URL.
No second call is needed to read them.
Inputs: powertrain (required). Returns: object
Solve a powertrain across a throttle or airspeed range, up to 25 points.
`sweep.steps` is the NUMBER OF POINTS, not a step size: start 40, stop 100,
steps 4 gives 40, 60, 80 and 100. One sweep beats a loop of single points.
The points come back in `result.points` with the share URL; no second call
is needed to read them.
Inputs: sweep (required), powertrain (required). Returns: object
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Read-only catalog of drone and eVTOL components: products, makers, specs and sources.
Real BEM engineering for propellers, wings and turbines — design, optimize, visualize, export.
Design, solve and simulate HVAC systems from real components, weather years and buildings.
Build, run and analyse block-diagram simulations: PID, Bode, FFT, optimisation and code export.
Add one secure layer between your agents and this server.