mixamo-llm-mocap

MCP音视频

提供方 squall01337 · 包名 mixamo-llm-mocap

音视频 stdio · 本地进程 未标注 社区 / 第三方 Claude DesktopCursorClineClaude Code
查看接入方式

Turn any video into a Mixamo-rig animation - GVHMR estimator, spec-driven retarget, FK apply in Blender via MCP. Works with any Mixamo character; built to be operated end-to-end by an AI agent.

一句话选型结论

按资料字段整理

mixamo-llm-mocap 属于音视频类 MCP 服务器,stdio · 本地进程,鉴权方式未标注,可直接接入 Claude Desktop、Cursor、Cline 等,有可直接执行的安装命令。接入前先确认权限范围;涉及写入、删除或付款的操作,建议先在测试环境验证。

分类音视频 传输方式stdio · 本地进程 鉴权未标注 部署方式本地部署
GitHub 星标 188 仓库热度,无公开仓库时显示未标注
工具数 未标注 暴露给模型的工具数量
资源 / 提示词 0 / 0 资源与提示词模板数量
维护方 社区 / 第三方 核验等级 仅资料核对

工具与能力

音视频
数量来自来源目录的标注,具体工具清单以官方文档为准
工具数量未标注暴露给模型可调用的工具个数
资源数量0可读取的资源条目
提示词数量0内置提示词模板数量

能力标签

ai-agent animation blender gvhmr llm

支持客户端

适用场景

ai-agentanimationblender

安装与配置

stdio · 本地进程 未标注
客户端在本机拉起子进程,数据不出本机
pip install mixamo-llm-mocap

这条命令只是入口,具体启动参数请按官方文档补齐,不要直接照搬到别的服务器。

  1. 1
    准备运行环境

    stdio 服务在本地起进程,需要先装好 Cross-platform,再按安装命令拉取依赖。

  2. 2
    安装服务

    复制上面的安装命令执行;命令里带占位符的位置,换成自己的密钥或路径。

  3. 3
    写入客户端配置

    在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,让新配置生效。

  4. 4
    验证是否可用

    连接成功后随便调一个只读工具,确认能返回结果,再接入正式流程。

典型使用场景

3 类
按分类与标签整理的常见用法,具体以官方文档为准
转写与字幕

把音视频转成文字和字幕。

音视频处理

裁剪、转码、拼接素材。

内容分发

把成品发到对应平台。

选择建议

选之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 有现成的安装命令,不用自己找入口,照着跑就能起服务。
  • 已适配 Claude Desktop、Cursor、Cline,换客户端不用重新研究配置。

先想清楚的地方

  • stdio 方式要求本地装好运行时(如 Node.js),换机器要重新装一遍。
  • 资料没标注工具数量,实际能力要装好后确认。
  • 版本更新与行为细节以官方仓库为准。

更适合

  • 需要在音视频场景里让模型直接调用外部能力的人。
  • 已经在用 Claude Desktop、Cursor 的用户,接入路径最短。
  • 想先快速试一下、能接受在本地或自有环境跑服务的人。

不太适合

  • 完全不想在本地装环境的人。
  • 需要厂商级 SLA 和技术支持的生产环境。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
MCP 服务器工具数传输方式部署方式安装命令最后核验
mixamo-llm-mocap当前 未标注 stdio · 本地进程 本地部署 有 2026-08-23
Ableton MCP B7b69a6a 16 stdio · 本地进程 本地部署 有 2026-05-17
Mini Max MCP 8 SSE · 服务端推送 远程部署 有 2026-05-18
LocalAI 未标注 stdio · 本地进程 本地部署 有 2026-04-11
Youtube E0eb3510 未标注 stdio · 本地进程 本地部署 有 2026-05-17
Voicemode MCP 未标注 stdio · 本地进程 本地部署 有 2026-05-17

服务器档案

音视频
字段来自项目仓库与公开索引,中文说明由本站标注
提供方squall01337上游标注的维护方 squall01337
分类音视频本站按上游分类展示
连接方式stdio · 本地进程客户端在本机拉起子进程,数据不出本机
鉴权方式未标注远程服务建议用最小权限凭据
维护方社区 / 第三方核验等级 仅资料核对
包名 / 运行时mixamo-llm-mocap · Cross-platform本地安装时用到的包标识与运行时
部署类型本地部署上游给出的部署形态
最近核验2026-08-23上游最后核验时间

详细介绍

11.5 KB
来自项目仓库与上游目录的原文,未做删改

Mixamo LLM Mocap

Turn any locked-camera video — filmed or AI-generated — into a clean
FK animation on any Mixamo character. One performer, or two fighting
each other. No mocap suit, no manual keyframing, and every stage
scriptable enough that an AI agent can run the whole loop.

Left: AI-generated source video. Right: the automatic retarget on a
Mixamo character in Blender — 10 seconds, nine punches, a slip under
and a high side kick, straight through the pipeline.

Two performers, one plate, one pass. The left fighter throws four
punches and a roundhouse; the right one blocks, folds over the body
shot and ducks under the kick. Both tracks are split out of the same
video by screen side, retargeted onto two Mixamo characters with
different proportions — Y Bot and Ninja — and placed at the distance
the performers actually stood, measured from the footage.

How it works

The default path transfers the estimator's SMPL-X joint rotations
and runs without the Blender UI:```
video plate (locked camera)
│
├─ 1. estimate_pose_gvhmr.py --smplx-only GVHMR → SMPL-X parameters, refined on the plate's 2D keypoints (+ heels/toes, + zoomed hands)
├─ 2. retarget_smplx.py rotations → your Mixamo rig; floor, foot locks, camera-true trajectory
├─ 3. bl_motion.py (blender -b) key the action in bulk and save it, or render — no MCP session
├─ 4. render_review.py 2×2 review video: plate | overlay on the plate / before | after, + hands & feet zoomed
└─ 5. eval_fidelity.py limb and head angles vs the video's keypoints, foot slide, jitter


- **Twist is real.** Forearm roll, spine curve and head orientation come
  from SMPL-X instead of being re-derived from positions.
- **Extremes survive.** GVHMR flattens fast limbs; a SMPLify-style fit on
  the plate's own ViTPose keypoints puts a head-high kick back at head
  height.
- **Feet point where the performer's point.** Heel and toe keypoints
  (MediaPipe) join the fit, and the rig's foot is aligned on the foot's
  real axis — toe-out, heel raises and pivots come from the video.
- **Feet stay down.** Contacts from GVHMR's detector, the floor, the
  image itself (a foot still on screen is planted) and physics (a foot
  carrying the body alone is planted, whatever the estimate says);
  planted feet lock flat or pivot on the point that carries the weight,
  and no foot goes under the floor.
- **Fingers from the video.** GVHMR has no fingers: each hand is cropped
  around its wrist, zoomed, and read by a hand detector; fists, open hands
  and the thumb follow the performer.
- **The trajectory is the camera's.** The plate's static camera is
  recovered; height drift is removed continuously and horizontal drift
  one footfall at a time, so the character ends on its mark.

The original landmark path below is still available for existing
specs and the two-character tooling:```
video plate (locked camera, T-pose bookends)
   │
   ├─ 1. estimate_pose_gvhmr.py    GVHMR (SMPL-X mesh recovery) → 33 landmarks + pelvis height
   ├─ 2. analyze_landmarks.py     numeric beat detection → you write a beat sheet from NUMBERS
   ├─ 3. action_specs/<name>.json  the motion as data: support schedule, rest blends, fists
   ├─ 4. lift_to_mixamo.py         direction-preserving retarget onto YOUR rig's proportions
   ├─ 5. apply_mixamo_fk.py        FK aim + foot planting, inside live Blender (via Blender MCP)
   ├─ 6. qa_clip.py                automated gate: no explosions, no pops, no foot skate
   ├─ 7. compare_reference.py      frame-by-frame vs the video → which windows still differ
   ├─ 8. compare_pair.py           two-character plates: separation, reach, intrusion
   ├─ 9. run_in_blender.py contact real mesh-vs-mesh collision between two characters
   └─ 10. render_preview.py        preview + side-by-side showcase video

With two performers in the plate, stages 1–7 run once per fighter
(--person left|right splits the tracks), setup_duo.py builds one
scene holding both characters, and compare_pair.py checks what only
exists when there are two of them: whether they stand, reach and miss
each other the way the performers did.

The estimator provides mesh-quality joints; the lift keeps its segment
directions but rebuilds every position from your character's measured
bone lengths; the apply plants feet by solving hip height (never IK —
Mixamo rigs are FK-only); the spec contributes only what a video cannot
know: which foot is the support in each phase (including "none" for
airborne beats), when fists close, where the clip locks back to rest.

Why it's different

  • Any Mixamo character. setup_rig.py builds a clean scene from
    your own Mixamo download and measures it into rig_profile.json
    (rest pose, bone lengths, hip and ground heights). Every stage reads
    that profile.
  • Motions are data, not code. A new motion is a small JSON spec —
    the action_specs/ here (a kung-fu form, a combo with a jump, a
    fight combination, a 360° jumping spin kick and a two-fighter duel)
    are worked examples of the whole schema.
  • Honest Mixamo FK. Hips are the only translating bone, everything
    else is quaternions at 30 fps — clips drop into any Mixamo-style
    workflow without cleanup.
  • Real ground contact. Planted feet solve to ground height with
    zero skate (the support ankle is pinned through each stance); jumps
    integrate the estimator's real pelvis arc.
  • A QA gate, not vibes. Exploded bones, hip pops, foot skate,
    drifting roots and broken rest poses are caught numerically before a
    human ever looks.
  • A closed refinement loop. compare_reference.py measures the
    retarget against the source video frame by frame on what an eye
    actually reads — hand height relative to the face, distance between
    the hands, limbs inside the torso, gaze direction — and reports the
    exact frame windows that diverge. Notes like "his hands are too high
    and his arm clips his back"
    become numbers, and an over-correction
    gets caught before it ships instead of after.
  • Two characters, one scene. A two-performer plate is split into
    tracks by which side of frame each occupies — robust where tracker
    ids swap on contact — retargeted onto two different Mixamo characters
    with their own measured proportions, and placed at the distance the
    performers actually stood, recovered from the footage rather than
    eyeballed. compare_pair.py then verifies separation, strike reach
    and limb intrusion against the video, frame by frame, and a Blender
    BVH pass checks the actual skinned meshes for collision — because two
    Mixamo characters are thicker than two humans, and a choreography
    built out of 2 cm near-misses collides when you retarget it faithfully.
    Clearance is bought from the stage with a declared, measured offset,
    which the comparator keeps reporting so the cost stays visible.
  • A review pass that is part of the loop. Render the showcase,
    put source and retarget side by side at the same beat, name what
    looks wrong in one sentence, then measure it. When eye and numbers
    disagree it is usually the numbers — every false reading in this
    project came from a mismatched proxy (a nose against a skull-base
    joint, a capsule against a mesh). docs/PIPELINE.md
    section 10.
  • Written for agents. Beat decisions come from
    analyze_landmarks.py numbers (never from eyeballing frames), every
    stage is a CLI or a socket call, and docs/PITFALLS.md encodes every
    mistake so the next operator — human or AI — doesn't repeat them.

Quickstart

  1. Install — docs/INSTALL.md walks through every
    dependency (list below).
  2. Build your rig scene:blender --background --python pipeline\setup_rig.py -- --fbx ybot.fbx --out ybot_rest.blend

  3. Run a plate — SMPL-X path (headless, no Blender window needed):tools\GVHMR\.venv\Scripts\python.exe pipeline\estimate_pose_gvhmr.py --video plates\<name>\<name>.mp4 --out plates\<name>\landmarks.json --smplx-only python pipeline\retarget_smplx.py --spec action_specs\<name>.json blender -b ybot_rest.blend -P pipeline\bl_motion.py -- apply --motion clips\<clip>\motion.npz --save clips\<clip>\<clip>.blend python pipeline\render_review.py --spec action_specs\<name>.json --clip clips\<clip> python pipeline\eval_fidelity.py --spec action_specs\<name>.json --clip clips\<clip>

A spec needs only name, action_name, clip_dir, landmarks and
the fps; fists, rest blends and arm_overrides are optional.
Details: docs/PIPELINE.md section S.

Or the landmark path (Blender open on the scene; plate rules in
docs/PROMPTING.md):tools\GVHMR\.venv\Scripts\python.exe pipeline\estimate_pose_gvhmr.py --video plates\<name>\<name>.mp4 --out plates\<name>\landmarks.json tools\GVHMR\.venv\Scripts\python.exe pipeline\analyze_landmarks.py --landmarks plates\<name>\landmarks.json # beat sheet → action_specs\<name>.json (schema: docs/PIPELINE.md) tools\GVHMR\.venv\Scripts\python.exe pipeline\lift_to_mixamo.py --spec action_specs\<name>.json python pipeline\run_in_blender.py all action_specs\<name>.json tools\GVHMR\.venv\Scripts\python.exe pipeline\qa_clip.py --spec action_specs\<name>.json tools\GVHMR\.venv\Scripts\python.exe pipeline\compare_reference.py --spec action_specs\<name>.json tools\GVHMR\.venv\Scripts\python.exe pipeline\render_preview.py action_specs\<name>.json --showcase

compare_reference.py tells you which frame windows still differ
from the video; the last command produces preview.mp4 and the
side-by-side showcase.mp4 — the same format as the demo GIF above.

Two-performer plates add --person left|right to the estimate, one
spec per fighter, and a compare_pair.py run — see
docs/PIPELINE.md section 9.

  1. Iterate with docs/PIPELINE.md and
    docs/PITFALLS.md.

What you need to bring (and where to get it)

What Where Notes
A Mixamo character — any model mixamo.com → Characters → download FBX Binary, T-pose Adobe's terms don't allow redistributing them; setup_rig.py builds and validates the scene from your download
Blender 5.1+ blender.org
Blender MCP add-on (official, Blender Lab) — landmark path only blender.org/lab/mcp-server enable Allow Online Access; the legacy apply talks to its socket. The SMPL-X path runs blender -b and needs no add-on
GVHMR (the pose estimator — not in this repo) github.com/zju3dv/GVHMR clone into tools/GVHMR; install per docs/INSTALL.md — including a working Windows recipe (docs/requirements_gvhmr_windows.txt + prebuilt pytorch3d wheel)
GVHMR checkpoints (~5 GB) HuggingFace mirror exact curl commands in docs/INSTALL.md
SMPL-X body model smpl-x.is.tue.mpg.de free research registration → download SMPL-X v1.1, place SMPLX_NEUTRAL.npz as shown in docs/INSTALL.md
GPU ~8 GB VRAM developed on an RTX 4080

Docs

Doc What it covers
docs/INSTALL.md Every dependency, step by step, Windows-proven
docs/PIPELINE.md The operational loop + the action_spec schema, field by field
docs/RIG.md Mixamo rig conventions: spaces, units, the rules that must never break
docs/PITFALLS.md Every mistake this pipeline's development paid for, so you don't pay twice
docs/PROMPTING.md Writing gen-video plate prompts that survive retargeting

License

MIT — see LICENSE, including third-party notes (Mixamo,
GVHMR, SMPL-X, Blender MCP).

常见问题

8 问
答案由本站依据条目字段整理,不引用上游原文
mixamo-llm-mocap 怎么安装?

在客户端按下面的安装命令接入:pip install mixamo-llm-mocap。对应的包名是 mixamo-llm-mocap。装完在客户端配置里引用同一个包或端点。

mixamo-llm-mocap 怎么在 Claude Desktop、Cursor、Cline 里配置?

它的传输方式是stdio · 本地进程,在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,配置才会生效。

mixamo-llm-mocap 收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于服务本身和背后的接口额度,正式使用前按官方说明确认。

mixamo-llm-mocap 需要 API Key 吗?

资料没有标注鉴权方式,是否需要密钥取决于服务本身,接入前按官方文档确认。

mixamo-llm-mocap 支持哪些客户端?

资料标注支持 Claude Desktop、Cursor、Cline、Claude Code;其他客户端只要能配置 MCP Server,也能用同样的命令或地址接入。

mixamo-llm-mocap 能提供哪些能力?

资料显示能力标签包括 ai-agent、animation、blender、gvhmr、llm。具体工具清单以官方文档为准。

mixamo-llm-mocap 需要什么运行环境?

运行时为 Cross-platform;属于本地进程,需要在本机装好运行环境。

mixamo-llm-mocap 是本地还是远程?

它是本地进程(stdio),由客户端在本机拉起。传输方式为stdio · 本地进程。

热门专题

按标签挑服务器
全部专题 →

服务器信息以作者仓库与官方文档为准;分类、传输方式与鉴权方式的中文说明为中文整理,最近核验 2026-08-23。