Rtkmotion MCP server
Which MCP servers are Rtkmotion's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-21
- Registry nameio.rtkmotion/dataverified in the MCP registry
The registry name sits under rtkmotion.io. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-21
- Tools22
- Server calls itselfRTK Motion MCP
- Server version1.0.0
- Protocol version2025-06-18
On 2026-10-21 the server answered initialize and tools/list without a sign-in. First answer in 150 ms.
- Whether its tools do the product's job has not been judged yet.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP score80 of 100answers 100 · definitions 83 · context 79 · use 8 · connects 100
- Use1 GitHub stars
- Answered100% of days8 of 8 daily checks
- Median first answer282 ms
- Space in an agent's context≈ 6,620 tokensthe definitions of all its tools (23), which an agent carries on every turn
- Tool definitionsB · 83 of 100
- Typed results0 of 23 toolsdeclared outputSchema: results come typed, read once
- Not saying whether it only reads or can destroy: 23 of 23
What an agent can do with it
- not sure · buy per-file motion capture for robot training
- not sure · generate biomechanical reports from exercise recordings
- not sure · check live threat levels around protected venues
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
browse_catalogBrowse hierarchical catalog of motion-capture, threat-intel, and rehab-biomechanics datasets. No path → root categories. Category path → children. Lesson path → file inventory, pricing, and MCP tool names. Free, no payment required.
get_bvhBVH skeletal animation for robotic_grappling_training or imitation_learning. 60 fps, 56-joint hierarchy with 3-segment finger chains, latency <500ms. Pay $10 USDC on Base (chain 8453, USDC 0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913) to…
get_video_urlMulti-view grappling video for pose_estimation_training or technique_analysis. 1080p synced cameras, 15-min signed streaming URL with Range support. Pay $5 USDC on Base (chain 8453, USDC 0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913) to RTK…
get_robotargetMulti-robot joint trajectories (NPZ) for sim_to_real_retargeting or imitation_learning. Platforms: Unitree G1 (43 DOF: 29 body + 14 hand), Unitree H1 (19 DOF), Apptronik Apollo (32 DOF) — specify via robot= param. MoveIt/ROS and Isaac Sim…
get_bundleComplete session bundle — EVERY modality for one lesson in a single purchase: all 12 camera views (1080p MP4), BVH skeletal animation for both subjects (60 fps, 56-joint), and robot-ready NPZ joint trajectories for every supported…
get_trial_bvhTRIAL — 5-second BVH skeletal sample (300 frames @ 60fps) from the Kimura side-control trial lesson. Same format as full $10 get_bvh — use to evaluate data quality before committing. Pay $0.25 USDC on Base (chain 8453, USDC…
get_trial_robotargetTRIAL — 5-second robot-trajectory sample (300 frames @ 60fps NPZ) from the Kimura side-control trial lesson. Same format as full $15 get_robotarget — use to evaluate retargeting quality before committing. Platforms: Unitree G1 (43 DOF: 29…
search_catalogFull-text search across motion-capture, threat-intel, and rehab-biomechanics datasets. Matches labels, paths, subject names, techniques. Returns full lesson detail with pricing so you can immediately call purchase tools. Free.
get_threat_summaryLocation threat assessment for risk_underwriting, facility_security_audit, or insurance_risk_modeling. Lite ($0.50): confidence-scored alerts, event distribution. Full ($1.00): + enriched entities, temporal context, corroboration scoring…
get_threat_profileMonitored location profile — assets, feed types, scan interval, term sets. Free — evaluate coverage and data freshness before purchasing threat assessments for risk_underwriting or security_operations.
get_rehab_summaryCross-exercise biomechanical summary for insurance_claim_validation or rehab_progress_tracking. Bilateral asymmetry indices, ROM for all major joints, fatigue markers, clinical synthesis identifying persistent deficits. JSON + TXT…
get_rehab_reportPer-exercise biomechanical report for PT_outcome_measurement or medical_insurance_review. CoM stability, rep detection, joint load, bilateral asymmetry, ROM, fatigue markers. JSON + TXT formats. Latency <200ms. Pay $0.25 USDC on Base…
get_rehab_profilePatient demographics, injury history, and medications for a rehab case. Free — evaluate case relevance before purchasing biomechanical reports for insurance_claim_validation or PT_outcome_measurement.
get_threat_sampleFREE live threat assessment sample — current threat level, confidence score, event distribution, and scan freshness for a monitored location. Proves data is live and continuously updated. No flagged items or entities (upgrade to…
get_rehab_sampleFREE rehab biomechanics sample — shows the structure and metric categories of a clinical summary without numeric values. Demonstrates data quality and coverage. Upgrade to get_rehab_summary ($0.50) for full numeric data. Try…
get_mocap_sampleFREE motion capture sample — first 5 seconds of BVH skeletal animation (frame count = 5 × lesson fps). Enough to validate format, joint hierarchy, and data quality for sim_to_real_retargeting or action_recognition. Full files are 20–120…
get_calibrationFREE multi-camera calibration parameters — intrinsics and extrinsics for the capture rig. Required for any pipeline that reprojects, retriangulates, or renders against the original capture geometry. Returns the .calib file as text.
get_spotter_carrier_profileCommercial-carrier sighting profile — USDOT, FMCSA carrier name, carrier class, sighting + image counts, geo coverage. Free — evaluate a carrier's sighting bundle before purchasing for carrier_identity_verification or…
get_spotter_carrierFull commercial-carrier sighting bundle for carrier_identity_verification, fleet_movement_corroboration, or cargo_fraud_investigation. Returns the structured sighting trail (USDOT, carrier, equipment, geo, timestamp) plus time-limited…
get_spotter_cv_profileCommercial-truck detection corpus profile — image count, label coverage, de-identification posture. Free — evaluate the training corpus before purchasing for detection_or_ocr_model_training.
get_spotter_cvGeo-stripped commercial-truck image corpus for detection_or_ocr_model_training. 1877 de-identified crops, every one a verified truck (equipment=truck on all 1877). FMCSA-public identity labels (usdot + carrier) are resolved on 90 crops…
get_spotter_cv_sampleTRIAL — a 10-crop slice of the geo-stripped commercial-truck detection corpus, to evaluate crop + de-identification quality before the full corpus (get_spotter_cv, $50). The corpus sells on verified truck crops; FMCSA-public usdot/carrier…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"data": {
"type": "http",
"url": "https://api.rtkmotion.io/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http rtkmotion https://api.rtkmotion.io/mcpclaude.ai, ChatGPT and other clients: add https://api.rtkmotion.io/mcp as a custom connector in the settings.
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.