RTK Motion — Motion Capture, Biomechanics, Threat & Fleet Intelligence

io.rtkmotion由 rtkmotion.io 發布官方發布者v1.3.0更新於 Nov 2, 2026

Mocap, rehab biomechanics, threat intel, fleet vision. 21 MCP tools, 10 free. x402/USDC paid.

已驗證Streamable HTTP可網頁執行金融資料與分析媒體與設計

概覽

AI 產生的概覽

託管型 MCP 伺服器,販售動作捕捉、復健生物力學、威脅情報與卡車目擊資料集,可免費瀏覽目錄、以 USDC 付費下載。

可以做什麼
  • 瀏覽並全文檢索資料集目錄,含課程路徑、檔案清單與價格
  • 取得免費樣本與概況:動捕 BVH 樣本、相機校正、威脅樣本與概況、復健檔案與樣本、承運商與 CV 語料概況
  • 購買付費動捕資料:BVH 骨骼動畫、多視角影片連結、機器人可用 NPZ 關節軌跡及整堂課綑綁包
  • 購買付費威脅情報與復健生物力學彙總及單一動作報告
  • 購買商業承運商目擊資料包與去除地理資訊的卡車 CV/OCR 訓練語料
  • 一次支付協商報價並兌換其中各項目
適用情境
當助理需要授權的人體動作或機器人重定向資料、臨床生物力學指標、地點威脅評估,或去識別化的商用卡車影像,且使用者願意按項以 USDC 付費時適用。可先用免費工具評估涵蓋範圍與資料品質再決定購買。
執行需求
遠端 streamable-HTTP 端點 api.rtkmotion.io/mcp,無需本機安裝。未宣告帳號或 API 金鑰。付費工具需要能支付 Base 鏈上 USDC 的加密錢包,可透過免 gas 的 x402 轉帳授權或已結算的鏈上交易雜湊完成;舊流程另列 Ethereum 與 Solana。
安裝前請注意
多數資料工具需實際支付 USDC,從 0.25 美元試用版到 50 美元完整 CV 語料,鏈上支付通常不可撤銷。購買需錢包與交易簽章,公布的收款地址與代幣合約屬第三方資料,應自行核實。復健工具回傳病患人口統計、受傷史與用藥資訊,威脅與承運商資料涉及真實地點和企業,應視為敏感資料處理。付費紀錄由提供方金鑰簽章,需自行驗證。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 RTK Motion — Motion Capture, Biomechanics, Threat & Fleet Intelligence,將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Web executable,透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式,或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南,先向你展示發布者、端點和登入方式,經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/io.rtkmotion%2Fdata/install.md,並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前,先告訴我它的發布者、端點和登入方式,等我確認。不要把 API 金鑰寫進命令或我會提交的檔案;問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "rtk-motion-motion-capture-biomechanics-t": {
      "type": "http",
      "url": "https://api.rtkmotion.io/mcp"
    }
  }
}

README

RTK Motion Intelligence — MCP Server

[smithery badge]

Agent-to-agent paid data marketplace. Two-person (dyadic) motion capture in a shared coordinate frame, rehab biomechanics, threat intelligence, and commercial-carrier truck-sighting intelligence (RTK Spotter). 21 MCP tools, gasless USDC payments via x402 (EIP-3009).

rtkmotion.io · Developer docs · Live catalog · Pricing · Shared-frame mocap spec

What is this?

A live, hosted Model Context Protocol server providing agent-to-agent paid access to:

  • 4D Motion Capture — BVH skeletal animation, multi-view video, robot-ready joint trajectories (NPZ). Two-person (dyadic) capture in a shared coordinate frame: both actors' global root translation and orientation are preserved in one capture-volume frame, so contact, separation and relative pose are recoverable directly from the files. Most released datasets canonicalize each actor to its own origin, which destroys inter-actor geometry irreversibly — see the specification and its pre-purchase verification procedure
  • Rehabilitation Biomechanics — cross-exercise summaries, per-exercise reports, ROM and asymmetry metrics
  • Location Threat Intelligence — confidence-scored alerts, event distribution, temporal context
  • RTK Spotter — Commercial Vehicle Intelligence — de-identified commercial-carrier truck sightings (per-USDOT bundles) plus a geo-stripped truck-recognition CV/OCR training corpus. Commercial carriers only; faces + bystander plates blurred; FMCSA-public labels (USDOT, carrier, equipment)

The server runs at https://api.rtkmotion.io/mcp on Cloudflare Workers, using the streamable-HTTP MCP transport.

This repository is the public-facing manifest for catalog discovery. The server itself is hosted, not installable from this repo.

Quick start

Add to Claude Desktop / Cursor / Cline / Continue

Add to your client's MCP config (e.g. ~/Library/Application Support/Claude/claude_desktop_config.json):

json
{  "mcpServers": {    "rtk-motion": {      "type": "streamable-http",      "url": "https://api.rtkmotion.io/mcp"    }  }}

Restart your client. The 21 tools become available.

See examples/ for ready-to-use config snippets and a minimal Python connect script.

Free tools (no payment, 10 total)

  • browse_catalog — hierarchical catalog of all data
  • search_catalog — full-text search across motion capture, rehab, threat, and Spotter datasets
  • get_mocap_sample — first 5 s of BVH skeletal animation (300 frames at 60 fps)
  • get_calibration — multi-camera capture-rig calibration
  • get_threat_profile — monitored location profile (assets, feeds, scan interval)
  • get_threat_sample — current threat assessment sample
  • get_rehab_profile — patient demographics, injury history, medications
  • get_rehab_sample — rehab biomechanics sample
  • get_spotter_carrier_profile — commercial-carrier coverage + de-identification posture
  • get_spotter_cv_profile — truck CV/OCR corpus profile (image count, label schema)

Paid tools (USDC via x402, 11 total)

ToolPriceOutput
get_bvh$10Full BVH skeletal animation
get_video_url$5Multi-view grappling video
get_robotarget$15Robot-ready joint trajectories (NPZ, MoveIt/ROS/Isaac compatible)
get_trial_bvh$0.25Trial BVH slice (5 s) — evaluate quality
get_trial_robotarget$0.25Trial NPZ trajectory (5 s) — evaluate quality
get_threat_summary$0.50 – $1.00Location threat assessment (lite / full)
get_rehab_summary$0.50Cross-exercise biomechanical summary
get_rehab_report$0.25Per-exercise biomechanical report
get_spotter_carrier$5Per-USDOT commercial-carrier sighting bundle (de-identified crops + trail)
get_spotter_cv_sample$0.25Trial slice of the truck CV/OCR corpus
get_spotter_cv$50Full geo-stripped truck-recognition CV/OCR training corpus

Payment in USDC via the x402 payment protocol. Which networks are available depends on the flow:

FlowNetworksHow
Gasless x402 exact / EIP-3009 (preferred)BaseAgent signs a single-use transfer authorization and passes it as x_payment — no gas for the buyer
On-chain payment_tx (legacy, MCP tools)Base · Ethereum · SolanaSend USDC, then supply the settled transaction hash
HTTP /paid/* routesBase onlyCDP-facilitated; the 402 challenge advertises eip155:8453

Full pricing detail at api.rtkmotion.io/pricing.

Provenance

Every paid record is signed with ECDSA (secp256k1) by 0x6C11F8a21f7ca922F483Ed21C3b6c2d9B305B10C. Verification key (JWKS) at api.rtkmotion.io/.well-known/jwks.json.

Discovery surfaces

Use cases

  • Robotics — Motion capture for sim-to-real kinematic retargeting (MoveIt/ROS/Isaac compatible NPZ trajectories). Dyadic captures support two-person interaction and contact-rich manipulation work that single-actor corpora cannot express
  • Human interaction / HOI modelling — Two-person motion in one shared coordinate frame, so contact, separation and relative pose are recoverable per frame rather than approximated
  • Insurance / Underwriting — Validate rehab claims with objective biomechanical data; assess facility risk via threat intelligence; vet commercial carriers via Spotter sighting bundles
  • Physical Therapy — Track patient progress with per-exercise biomechanical reports
  • Security & Compliance — Location threat audits, confidence-scored alerting
  • Fleet & Logistics / Computer Vision — Commercial-carrier movement corroboration and cargo-fraud investigation from de-identified truck sightings; train truck-recognition detection/OCR models on the geo-stripped CV corpus

Latency

< 500 ms typical for free tools. Cloudflare Workers global edge deployment.

Specifications

  • Shared-Frame Multi-Actor Motion Capture — a delivery specification — a vendor-neutral spec for delivering multi-actor mocap without destroying inter-actor geometry, with a pre-purchase verification procedure a buyer can run against any supplier. Draft, published for comment. Canonical URL: https://github.com/RTKMotion/motion-intelligence/blob/main/docs/SHARED_FRAME_MOCAP_SPEC.md

Source

This is a manifest repository for the hosted MCP server. The server implementation runs on Cloudflare Workers; the implementation source is private. For technical questions, partnership, or custom integration: [email protected].

License

The contents of this repository (README, examples, configuration files) are released under the MIT License — see LICENSE.

The data products served by the MCP server are separately licensed via the per-purchase terms documented at api.rtkmotion.io/.well-known/x402 and at rtkmotion.io/legal.

來源:README.md,提交 d363bbc

工具

23

browse_catalog

Browse 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.

輸入參數path

get_bvh

BVH 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 RTK wallet 0x6C11F8a21f7ca922F483Ed21C3b6c2d9B305B10C; pass tx hash as payment_tx. Eth/Solana: /.well-known/x402. Cheaper $0.25 trial sample: call get_trial_bvh.

輸入參數subject必填quote_idx_paymentpayment_txlesson_path

get_video_url

Multi-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 wallet 0x6C11F8a21f7ca922F483Ed21C3b6c2d9B305B10C; pass tx hash as payment_tx. Eth/Solana: /.well-known/x402.

輸入參數view必填quote_idx_paymentpayment_txlesson_path

get_robotarget

Multi-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 compatible, 60 fps, latency <500ms. Pay $15 USDC on Base (chain 8453, USDC 0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913) to RTK wallet 0x6C11F8a21f7ca922F483Ed21C3b6c2d9B305B10C; pass tx hash as payment_tx. Eth/Solana: /.well-known/x402. Cheaper $0.25 trial sample: call get_trial_robotarget.

輸入參數robotsubject必填quote_idx_paymentpayment_txlesson_path

get_bundle

Complete 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 platform (Unitree G1 43 DOF, Unitree H1 19 DOF, Apptronik Apollo 32 DOF). 20 files, ~$170 bought individually. Does NOT include the rigged FBX/OBJ mesh assets, which are licensed separately via Fab.com. Pay $50 USDC on Base (chain 8453, USDC 0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913) to RTK wallet 0x6C11F8a21f7ca922F483Ed21C3b6c2d9B305B10C; pass tx hash as payment_tx. Solana USDC to 7vV3cV7iCtmwKCzK1tWRdbWop31zw7pVFe8HxfFKrTZV also accepted — pass the base58 signature as payment_tx. See /.well-known/x402.

輸入參數quote_idx_paymentpayment_txlesson_path

pay_quote

Pay for a negotiated quote from the RTK seller agent in one payment, then redeem each item with its normal tool. The quote is a signed token (rtkq1.…) listing items, list prices, the agreed discount (at most 10%) and the total. This tool verifies the quote, takes a single payment for exactly its total, and returns a `redeem` list: call each tool shown with the arguments shown (they include quote_id) to receive the item, with no further payment. Pay the quote total in USDC on Base (chain 8453, USDC 0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913) to RTK wallet 0x6C11F8a21f7ca922F483Ed21C3b6c2d9B305B10C: preferred is a gasless EIP-3009 authorization as x_payment, otherwise pass the tx hash as payment_tx. Solana USDC to 7vV3cV7iCtmwKCzK1tWRdbWop31zw7pVFe8HxfFKrTZV is also accepted as payment_tx. Calling again with a quote that is already paid returns the same redeem list without charging.

輸入參數quote必填x_paymentpayment_tx

get_trial_bvh

TRIAL — 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 0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913) to RTK wallet 0x6C11F8a21f7ca922F483Ed21C3b6c2d9B305B10C; pass tx hash as payment_tx. Eth/Solana: /.well-known/x402.

輸入參數subjectquote_idx_paymentpayment_tx

get_trial_robotarget

TRIAL — 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 body + 14 hand), Unitree H1 (19 DOF), Apptronik Apollo (32 DOF). Pay $0.25 USDC on Base (chain 8453, USDC 0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913) to RTK wallet 0x6C11F8a21f7ca922F483Ed21C3b6c2d9B305B10C; pass tx hash as payment_tx. Eth/Solana: /.well-known/x402.

輸入參數robotsubjectquote_idx_paymentpayment_tx

search_catalog

Full-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.

輸入參數query必填subjectvertical

get_threat_summary

Location 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. Latency <200ms. Pay USDC on Base (chain 8453, USDC 0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913) to RTK wallet 0x6C11F8a21f7ca922F483Ed21C3b6c2d9B305B10C; pass tx hash as payment_tx. Eth/Solana: /.well-known/x402. Browse ThreatIntel via browse_catalog first.

輸入參數tierregionlocation必填quote_idx_paymentpayment_tx

get_threat_profile

Monitored 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.

輸入參數regionlocation必填

get_rehab_summary

Cross-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 formats. Latency <300ms. Pay $0.50 USDC on Base (chain 8453, USDC 0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913) to RTK wallet 0x6C11F8a21f7ca922F483Ed21C3b6c2d9B305B10C; pass tx hash as payment_tx. Eth/Solana: /.well-known/x402.

輸入參數quote_idcase_path必填x_paymentpayment_tx

get_rehab_report

Per-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 (chain 8453, USDC 0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913) to RTK wallet 0x6C11F8a21f7ca922F483Ed21C3b6c2d9B305B10C; pass tx hash as payment_tx. Eth/Solana: /.well-known/x402.

輸入參數exercise必填quote_idcase_path必填x_paymentpayment_tx

get_rehab_profile

Patient 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.

輸入參數case_path必填

get_threat_sample

FREE 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_threat_summary for full detail). Try location='culpeper-town' or browse_catalog path='ThreatIntel' for all locations.

輸入參數location

get_rehab_sample

FREE 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 case_path='PhysicalRehab/40-50/Male/LabrumTear'.

輸入參數case_path

get_mocap_sample

FREE 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 seconds ($10 USDC via get_bvh).

輸入參數subjectlesson_path

get_calibration

FREE 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.

輸入參數lesson_path

get_spotter_carrier_profile

Commercial-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 cargo_fraud_investigation.

輸入參數usdot必填

get_spotter_carrier

Full 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 signed URLs to every de-identified truck crop (faces + bystander plates blurred). Where the subject truck is confirmed by its own USDOT/carrier markings, its plate is left unaltered; on any frame we cannot tie a plate to that confirmed truck, every plate is blurred. In practice MOST frames carry no legible plate at all — buy this for the sighting trail, not for plates. `equipment` is capture-derived and approximate. RTK distributes NO plate interpretation at all — no plate text or state in any record, and no plate-keyed lookup exists. Commercial carriers only — owner-operators excluded by disclosure policy. Pay $5 USDC on Base (chain 8453, USDC 0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913) to RTK wallet 0x6C11F8a21f7ca922F483Ed21C3b6c2d9B305B10C; pass tx hash as payment_tx. Eth/Solana: /.well-known/x402. Free evaluation: get_spotter_carrier_profile.

輸入參數usdot必填quote_idx_paymentpayment_tx

get_spotter_cv_profile

Commercial-truck detection corpus profile — image count, label coverage, de-identification posture. Free — evaluate the training corpus before purchasing for detection_or_ocr_model_training.

無需輸入參數。

get_spotter_cv

Geo-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 (4.8%) and null on the rest — treat them as a bonus, not the basis of the corpus. Returns labels (JSONL, one row per crop — no plate read, no geo, no timestamp) plus time-limited signed URLs to the de-identified truck crops (faces/persons + non-subject text + burned-in GPS blurred, and EVERY plate blurred including the subject truck's own; only painted carrier markings remain). Pay $50 USDC on Base (chain 8453, USDC 0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913) to RTK wallet 0x6C11F8a21f7ca922F483Ed21C3b6c2d9B305B10C; pass tx hash as payment_tx. Eth/Solana: /.well-known/x402. Images are paged — use offset to page through the corpus with the same payment_tx.

輸入參數limitoffsetquote_idx_paymentpayment_tx

get_spotter_cv_sample

TRIAL — 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 are resolved on only 90 of 1877 crops (4.8%) and this fixed trial slice lands in the unlabeled majority, so expect usdot/carrier to be null here — judge the IMAGES, not the identity fields. Returns 10 label rows + time-limited signed URLs to those 10 de-identified crops (faces/persons + non-subject text + burned-in GPS blurred). Pay $0.25 USDC on Base (chain 8453, USDC 0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913) to RTK wallet 0x6C11F8a21f7ca922F483Ed21C3b6c2d9B305B10C; pass tx hash as payment_tx. Eth/Solana: /.well-known/x402. Free preview: get_spotter_cv_profile.

輸入參數quote_idx_paymentpayment_tx

版本歷史

1
  1. v1.3.0最新Sep 16, 2026

評分

已滿足適用檢查項的 100%

該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分