What can you do with this server?

The CtrlTest MCP Server provides automated control system evaluation and regression testing for PID and bio-inspired controllers in flapping-wing aircraft systems, exposing a standardized API (ctrltest.analyze_pid) for comprehensive performance analysis. Core Capabilities: * PID Controller Analysis - Evaluate PID gains against plant dynamics (natural frequency, damping ratio) to measure overshoot, settling time, integral squared error (ISE), and Lyapunov stability margins * High-Fidelity Simulation Integration - Ingest data from diffSPH (differentiable smoothed-particle hydrodynamics) and Foam-Agent CFD simulations via extra_metrics for realistic performance assessment * Multi-Modal Scoring - Fuse analytic models with high-fidelity simulation data when both diffSPH and Foam-Agent metrics are available * Gust Rejection Analysis - Quantify disturbance handling through gust detection latency, bandwidth, and rejection percentage metrics * Energy Efficiency Assessment - Measure CPG (Central Pattern Generator) baseline vs. consumed energy and calculate energy reduction percentages * Mix-of-Experts Evaluation - Compute switching penalties, latency budgets, and energy consumption for adaptive control architectures * Automated Integration - Support continuous performance monitoring, automated gain tuning, and controller optimization through STDIO/HTTP API integration with ToolHive, RL algorithms, and evolutionary systems * Structured Output - Export JSON-formatted results with provenance metadata for dashboards, logging, and downstream analysis

Which integrations are available for this server?

Provides a REST API interface for the control system evaluation service, allowing HTTP-based access to controller benchmarking and scoring functionality. Enables visualization of controller performance metrics and analytics data exported from PID evaluations and comparative controller assessments.

How do I use CtrlTest MCP Server?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@CtrlTest MCP Server evaluate PID gains kp=2.0, ki=0.5, kd=0.12 for a second-order plant with natural frequency 3.2Hz" 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.

ctrltest-mcp - Flight-control regression lab for MCP agents

TL;DR: Evaluate PID and bio-inspired controllers against analytic or diffSPH/Foam-Agent data through MCP, logging overshoot, energy, and gust metrics automatically.

What it provides

Scenario	Value
Analytic PID benchmarking	Run closed-form plant models and produce overshoot/settling/energy metrics without manual scripting.
High-fidelity scoring	Ingest logged data from Foam-Agent or diffSPH runs and fuse it into controller evaluations.
MCP integration	Expose the scoring API via STDIO/HTTP so ToolHive or other clients can automate gain tuning and generate continuous performance scorecards.

Quickstart

uv pip install "git+https://github.com/Three-Little-Birds/ctrltest-mcp.git"

Run a PID evaluation:

from ctrltest_mcp import (
    ControlAnalysisInput,
    ControlPlant,
    ControlSimulation,
    PIDGains,
    evaluate_control,
)

request = ControlAnalysisInput(
    plant=ControlPlant(natural_frequency_hz=3.2, damping_ratio=0.35),
    gains=PIDGains(kp=2.0, ki=0.5, kd=0.12),
    simulation=ControlSimulation(duration_s=3.0, sample_points=400),
    setpoint=0.2,
)
response = evaluate_control(request)
print(response.model_dump())

Typical outputs (analytic only):

{
  "overshoot": -0.034024863556091134,
  "ise": 0.008612387509182674,
  "settling_time": 3.0,
  "gust_detection_latency_ms": 0.8,
  "gust_detection_bandwidth_hz": 1200.0,
  "gust_rejection_pct": 0.396,
  "cpg_energy_baseline_j": 12.0,
  "cpg_energy_consumed_j": 7.8,
  "cpg_energy_reduction_pct": 0.35,
  "lyapunov_margin": 0.12,
  "moe_switch_penalty": 0.135,
  "moe_latency_ms": 12.72,
  "moe_energy_j": 3.9,
  "multi_modal_score": null,
  "extra_metrics": null,
  "metadata": {"solver": "analytic"}
}

The analytic plant example above clips settling_time at the requested simulation duration (duration_s=3.0). Increase the horizon if you need the loop to settle fully before computing that metric.

Run as a service

CLI (STDIO transport)

uvx ctrltest-mcp  # runs the MCP over stdio
# or just python -m ctrltest_mcp

Use python -m ctrltest_mcp --describe to print basic metadata without starting the server.

FastAPI (REST)

uv run uvicorn ctrltest_mcp.fastapi_app:create_app --factory --port 8005

python-sdk tool (STDIO / MCP)

from mcp.server.fastmcp import FastMCP
from ctrltest_mcp.tool import build_tool

mcp = FastMCP("ctrltest-mcp", "Flapping-wing control regression")
build_tool(mcp)

if __name__ == "__main__":
    mcp.run()

ToolHive smoke test

Run the integration script from your workspace root:

uvx --with 'mcp==1.20.0' python scripts/integration/run_ctrltest.py

The smoke test runs the analytic path by default. To exercise high-fidelity scoring, stage Foam-Agent archives under logs/foam_agent/ and diffSPH gradients under logs/diffsph/ before launching the script.

Agent playbook

Gust rejection - feed archived diffSPH gradients (diffsph_metrics) and Foam-Agent archives (paths returned by those services) to quantify adaptive CPG improvements.
Controller comparison - log analytics for multiple PID gains, export JSONL evidence, and visualise in Grafana.
Policy evaluation - integrate with RL or evolutionary algorithms; metrics are structured for automated scoring.

Stretch ideas

Extend the adapter for PteraControls (planned once upstream Python bindings are published).
Drive the MCP from scripts/fitness to populate nightly scorecards.
Combine with migration-mcp to explore route-specific disturbance budgets.

Accessibility & upkeep

Run uv run pytest (tests mock diffSPH/Foam-Agent inputs and assert deterministic analytic results).
Keep metric schema changes documented—downstream dashboards rely on them.

Metric schema at a glance

Field	Units	Notes
`overshoot`	radians	peak response minus setpoint
`ise`	rad²·s	integral squared error
`settling_time`	seconds	first time error stays within tolerance
`gust_detection_latency_ms`	milliseconds	detector latency
`gust_detection_bandwidth_hz`	hertz	detector bandwidth
`gust_rejection_pct`	0–1	fraction of disturbance rejected
`cpg_energy_baseline_j`	joules	energy pre-adaptation
`cpg_energy_consumed_j`	joules	energy post-adaptation
`cpg_energy_reduction_pct`	0–1	energy reduction ratio
`lyapunov_margin`	unitless	stability margin
`moe_switch_penalty`	unitless	cost weight × switches
`moe_latency_ms`	milliseconds	latency budget after switching
`moe_energy_j`	joules	mix-of-experts energy draw
`multi_modal_score`	unitless	only when both diffSPH & Foam metrics are present
`extra_metrics`	varies	raw diffSPH/Foam metrics merged in

Example of fused high-fidelity metrics:

{
  "extra_metrics": {
    "force_gradient_norm": 0.87,
    "lift_drag_ratio": 18.4
  },
  "multi_modal_score": 0.047,
  "metadata": {"solver": "analytic"}
}

Contributing

uv pip install --system -e .[dev]
uv run ruff check . and uv run pytest
Share sample metrics in PRs so reviewers can sanity-check improvements quickly.

MIT license - see LICENSE.

Available Tools

1 tool

ctrltest.analyze_pidC

Score PID gains for a flapping-wing plant. Provide plant dynamics and optional gradients/metadata. Returns key control metrics plus provenance. Example input: {"plant":{"natural_frequency_hz":4.2,"damping_ratio":0.45},"gains":{"kp":1.1,"ki":0.2,"kd":0.08},"diffsph_metrics":{"force_gradient_norm":1.9}}

Inputs: request (required). Returns: ise, metadata, overshoot, moe_energy_j, +12 more

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

Deploy Server

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

TDQS

B3.1/5.0

Scored 2026-04-18 08:15 across 1 tool

Disambiguation5/5

With only one tool, there is no possibility of ambiguity or overlap between tools. The tool's purpose is clearly defined as analyzing PID gains for a specific type of plant, making it distinct by default.

Naming Consistency5/5

The single tool name follows a consistent pattern with a clear namespace prefix (ctrltest) and descriptive action (analyze_pid). With only one tool, naming consistency is inherently perfect as there are no other tools to compare against.

Tool Count2/5

A single tool is generally too few for most server purposes, as it limits functionality and forces agents to rely on one operation. While it might be appropriate for a highly specialized task, the server's name 'CtrlTest MCP Server' suggests a broader control testing domain where more tools would be expected for completeness.

Completeness2/5

The server appears focused on control system testing, but with only one analysis tool, there are significant gaps. Missing operations likely include tools for setting up tests, running simulations, comparing results, or managing test configurations, making the surface severely incomplete for the implied domain.

Maintenance

ActivityInactive

ResponsivenessNo recent community issues

Resources

Related MCP Connectors

BlockWerkB
tech.blockwerk
Build, run and analyse block-diagram simulations: PID, Bode, FFT, optimisation and code export.
Data Visualization Developer Tools
421
https://blockwerk-mcp-worker.blockwerk.workers.dev/
MakerPortal computeA
ai.makerportal
Deterministic engineering solvers: biquad filter design, room eigenmodes, LLM VRAM fit.
Audio Processing AI & Machine Learning
81
https://makerportal.ai/api/mcp
PLC Cloud Sim — LAD/SCL simulation over MCP
io.github.tia-forge
Cloud PLC simulator: validate and step-run LAD/SCL programs, run scenarios, return PASS/FAIL.
Code Execution Developer Tools Testing & QA Tools
1
https://tia.hubwiz.com/sim/mcp
UpToCode
io.github.DDYRich72
Evidence-backed architecture-quality analysis for Python agent applications.
Code Analysis Developer Tools Software Architecture
2
https://uptocode-mcp-1015314816960.us-central1.run.app/mcp

Related MCP Servers

shewhart-mcp
Research & Data Data Visualization
bertanucar
A
license
Not graded
quality
D
maintenance
Enables AI agents to perform statistical process control calculations using validated, deterministic tools such as control charts, capability analysis, and tolerance intervals.
Updated 5 months ago (2026-06-12 11:25 UTC)
3
MIT
kshana-mcp
Aerospace & Astrodynamics Research & Data
ashfordeOU
A
license
Not graded
quality
C
maintenance
Validated PNT-resilience simulator over MCP — SGP4/SDP4 orbit propagation, IAU reference frames, GNSS availability/DOP, GNSS/INS fusion, ARAIM integrity, and Allan deviations, with results validated against AIAA/IGS/SOFA/NIST reference data.
Updated 17 hours ago (2026-11-10 01:11 UTC)
664 PyPI
9
AGPL 3.0
agent-eval-mcp
Testing & QA Tools CI/CD & DevOps AI & Machine Learning
ad-github1
A
license
B
quality
D
maintenance
An MCP-style stdio server for evaluating AI agent outputs, enabling CI-friendly quality gates, regression comparisons, and canary promotion decisions.
Updated 4 months ago (2026-06-29 10:09 UTC)
3
MIT
evalsmith-mcp
RAG Systems Testing & QA Tools CI/CD & DevOps
diegoperezg7
A
license
A
quality
B
maintenance
Enables MCP clients to score retrieval quality with recall, precision, nDCG, hit rate and MRR, compare 2-3 configurations with seeded paired-bootstrap confidence intervals, audit agent tool calls against expected traces, and detect prompt regressions against golden sets. It also generates Markdown, JSON or JUnit reports with pass/fail gates, all deterministically and offline without paid API keys.
Updated 6 days ago (2026-11-04 15:36 UTC)
6
172 npm
1
MIT