owlsightMCP
Supports using local Ollama vision models as the drone verifier, either through retriEVAL's judge backend or directly via DRONE_VERIFIER=ollama, to privately evaluate camera frames and claims.
Allows calling an OpenAI vision model directly as the verifier via DRONE_VERIFIER=openai, without requiring retriEVAL, to check camera frames and mission claims.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
GroundTruthVision
Powered by retriEVAL.
Fly a small drone from Claude, Cursor or any MCP client, and never take its word for what it saw. The drone flies; retriEVAL evaluates, live. A safety gate the AI can't talk its way past keeps the flight safe; retriEVAL decides what the camera really shows before the drone acts on it or reports it.
It runs in a simulator today and is built to swap in a Tello EDU.
The idea
"Find the blue backpack."
The drone takes off and turns on the spot, looking.
A fast detector spots candidates on every frame. It knows backpack, not blue, so a black backpack fools it.
For each candidate the drone hovers while retriEVAL scores the claim "There is a blue backpack in view" against the frame with its
visual_faithfulnessmetric. It splits the claim into parts ("a backpack", "it is blue") and checks each: the black backpack scores 0.5 and is rejected, the blue one scores 1.0 and is confirmed.It turns to face the target and flies to about a metre away. Mid-flight,
check_claimlets Claude have retriEVAL check anything it is about to say ("the backpack is on the couch") against what the camera sees now.After landing,
report_missionsends Claude's report to retriEVAL with two kinds of evidence: the frames the camera captured, and the flight log as plain sentences. "Found the blue backpack" passes because a frame shows it; "flew 262 cm" passes because the log records it. Each claim says which backed it. Anything neither supports comes backaccepted: falsewith the claims to fix.
Related MCP server: tello-mcp
Layers
Claude ──MCP──> server.py the tools Claude calls
mission.py runs every action through the steps below, keeps the log
safety.py SafetyGate: refuses unsafe commands before they fly
perception.py Detector: fast candidates on every frame
retrieval.py ──MCP──> retriEVAL: scores candidates, claims, the report
drone.py SimDrone, or tello.py for the real Tello EDUGroundTruthVision talks to retriEVAL MCP to MCP: it starts retriEVAL as a local server and keeps one session open for the flight. Local, because the frames are files on this computer.
The rule: Claude decides where to go, the safety gate decides whether it's allowed, and the gate always wins. Refusals come back as plain sentences Claude can act on ("that move would leave the flight box"), and nothing is flown.
Tools
Tool | What it does |
| New mission and a fresh flight log; says which evaluator is in use |
| Take off to ~80 cm; land |
| forward, back, left, right, up, down; 20-200 cm |
| Positive turns right, negative left |
| What the detector sees right now (candidates only) |
| Turn and look; hover while retriEVAL checks each candidate; stop on a confirmed match |
| Fly toward a confirmed target, stop ~1 m away |
| retriEVAL checks a claim against what the camera sees now |
| Position, height, heading, battery, clock |
| Cut the motors. On a real drone it drops |
| retriEVAL checks the report against the mission's frames; save the log |
| Saved missions, newest first: goal, what was confirmed, look-alikes rejected, report verdict |
| Open a saved flight: every retriEVAL check with its score and reason; |
Safety limits
Set by environment variables; defaults suit a small drone indoors.
Variable | Default | Meaning |
| 200 | Ceiling |
| 30 | Lowest it may fly; below that, land |
| 200 | Longest single move |
| 40 | Keep-out distance from the flight box edge |
| 20 | Below this it refuses moves and lands itself |
| 30 | Minimum battery to take off |
| 400 | Real drone: size of the flight box around take-off |
Landing and emergency stop are never refused.
Run it in the simulator
pip install -r requirements.txt
python -m pytest -q # 33 tests, no drone, network or API key needed
python run.py # MCP over stdioCursor (~/.cursor/mcp.json) or Claude Desktop:
{
"mcpServers": {
"groundtruthvision": {
"command": "/Users/hcarrillo/Workspace/groundtruthvision-mcp/.venv/bin/python",
"args": ["/Users/hcarrillo/Workspace/groundtruthvision-mcp/run.py"],
"env": {
"RETRIEVAL_SERVER": "/Users/hcarrillo/Workspace/retrieval-mcp/retrieval-mcp/server.py",
"RETRIEVAL_PYTHON": "/Users/hcarrillo/Workspace/retrieval-mcp/.venv/bin/python",
"RETRIEVAL_JUDGE": "nemotron",
"OPENROUTER_API_KEY": "sk-or-..."
}
}
}
}Then ask: "Start a mission to find the blue backpack, take off, scan for it, approach it, land, and report what you found."
The simulated room is sim/worlds/living_room.json. Its camera shows the
pictures in sim/photos; replace them with photos of your own room and
retriEVAL judges real images.
The evaluator: retriEVAL
retriEVAL is the evaluator whenever GroundTruthVision can find it. Point GroundTruthVision at your retriEVAL checkout and give retriEVAL a judge that can see images:
Variable | Meaning |
| Path to retriEVAL's |
| A Python with retriEVAL's requirements installed (default: GroundTruthVision's own) |
|
|
Judges for these checks:
Judge | Setup | When |
NVIDIA Nemotron |
| Developing: free, rate limited (~20/min), may log images |
Claude |
| Accurate; paid |
Local vision model |
| Real flights over your home: free, private, no rate limits |
Each check's time is recorded as hover_s in the flight log, so you can
measure your setup before flying.
DRONE_VERIFIER overrides the choice: retrieval (the default when retriEVAL
is found), sim (the simulator's stand-in, no keys needed), or ollama /
openai to call a vision model directly without retriEVAL.
Real Tello EDU (next)
pip install djitellopy opencv-python ultralytics
python tello_join_wifi.py "Home WiFi" "password" # once, while joined to the Tello's own Wi-Fi
DRONE_DRIVER=tello TELLO_HOST=192.168.1.57 python run.py # the address your router gave the TelloThe Tello and this computer must be on the same 2.4 GHz network, not a guest
network (guest networks usually stop devices seeing each other). Reserve the
Tello's address in your router so TELLO_HOST stays right. The computer's
firewall must let UDP ports 8889, 8890 and 11111 in (commands, state, video).
tello.py and yolo.py (YOLO-World, an open-vocabulary detector) implement the
same interfaces as the simulator but are untested until they meet real
hardware. The Tello has no GPS: position is dead reckoning from the commanded
moves, so keep the wall margin generous. Put the Tello EDU on your home Wi-Fi
(station mode) so this computer keeps its internet connection.
Not built yet
Railway relay: the server running on Railway with the laptop bridge dialling out to it over a WebSocket with signed commands.
Distance sensing on the Tello: it has no rangefinder, so
approachrelies on an estimate from the camera and the wall margin.Jev for fusing detections into decisions, to be compared against plain rules on recorded flights.
Showing the report's frames on retriEVAL's report page (it lists the claims and verdicts today, not the images).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
Zero-secret MCP gateway for AI agents: risk-scored, audited calls with human-in-the-loop approval.
MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.
Control plane for autonomous software labor. Agents claim objectives over MCP with audit trail.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables natural language control of a simulated drone for search missions, with tools for takeoff, movement, scanning, and landing via MCP.2-
- FlicenseNot gradedqualityDmaintenanceMCP server that connects a local LLM to a DJI Tello drone via UDP, enabling natural language flight planning and execution with safety-focused separation of plan and execution, plus a full simulator for development.-
- AlicenseAqualityDmaintenanceConnects AI agents to MAVLink drones (PX4, ArduPilot) via a capability layer with safety guardrails, enabling telemetry, flight control, and mission management through natural language.122MIT
- AlicenseNot gradedqualityCmaintenanceA lightweight, air-gapped desktop cockpit connecting local LLMs (Llama 3.2) to standard MCP tools with deterministic hardware safety, acting as an edge-native MCP control plane and autonomous tool dispatcher.2MIT