Figma Context MCP
Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.
作者提供的说明(英文原文)
Measured spatial answers for posing first-person arms and a rifle in Blender
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
POSELAB_BLENDER, POSELAB_RIGS, POSELAB_OUT你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"poselab": {
"command": "uvx",
"args": [
"poselab-mcp"
],
"env": {
"POSELAB_BLENDER": "your-value",
"POSELAB_RIGS": "your-value",
"POSELAB_OUT": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add poselab --env POSELAB_BLENDER=your-value --env POSELAB_RIGS=your-value --env POSELAB_OUT=your-value -- uvx poselab-mcp运行前请先填写空着的值。
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"poselab": {
"command": "uvx",
"args": [
"poselab-mcp"
],
"env": {
"POSELAB_BLENDER": "your-value",
"POSELAB_RIGS": "your-value",
"POSELAB_OUT": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"poselab": {
"type": "stdio",
"command": "uvx",
"args": [
"poselab-mcp"
],
"env": {
"POSELAB_BLENDER": "your-value",
"POSELAB_RIGS": "your-value",
"POSELAB_OUT": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
你的选择通过 Cookie 保存在这台设备上,无需账户。
POSELAB_BLENDER envPOSELAB_RIGS envPOSELAB_OUT env这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月7日
注册名称已通过 GitHub 账户 hpdkhoa 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于–,最新版本(0.7.0)于23天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Python (uv)。
同一分类中有:Figma Context MCP, Claude Real Video, Figma MCP Server
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.
Let any LLM watch a video locally — and search everything it has ever watched.
The Figma MCP server brings Figma design context directly into your AI workflow.
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
Pose Lab
Measured spatial answers for posing first-person arms and a rifle in Blender.
Models are weak at judging 3D space from pictures: which side of a rifle faces the eye, whether a finger sits inside the receiver, whether any turn of the gun can ever show its ejection port. Pose Lab gives a model numbers instead. It reports positions in named frames and how deep anything clips. It measures how squarely a surface faces the eye and what the eye can see. Its solver searches rifle moves against goals and reports which goals no move can meet. For animation, it scans a clip frame by frame against the same checks and mends what fails.
I built it while hand-making chamber checks for my first-person shooter. One question took me several full Blender runs: can turning the rifle show its ejection port to the eye? With Pose Lab it is one solve call. On my game's AK rig, turning alone met the goal in 0 of 60 samples. That is a fact of the geometry: the eye looks along the barrel. Turning and moving the rifle met each goal on its own, but no sample of 400 met all four goals together. So that check needs a new hand pose, not only a new rifle position. On the built-in sample rig, turning alone also met the port goal in 0 of 60 samples, and turning and moving met every goal in 9 s.
| Tool | Answers |
|---|---|
list_rigs, load_rig, describe | the rigs, the frames, the sign rules, named points, clips, moving parts |
pose_idle, pose_clip, move_part, snapshot | put the rig in a pose: a clip at a time, the carrier drawn back, saved poses |
move_gun | roll, swing, pitch and move the rifle; the hands keep their hold by arm IK |
reach | a wrist onto a point by arm IK (try elbow poles to clear a forearm) |
turn_bone | one bone turned about an axis through its head: a finger joint, a wrist, a whole arm |
where, distance | positions in a named frame |
clearance | how deep the rifle sits inside a forearm, palm or finger, measured to its surface, and where |
purpose | every hand works on a target: holds (pinch or wrap), pulls (pinch or hook), presses, rests on or reaches for a part; no finger curled around nothing |
anatomy | each arm against the human arm's limits: elbow, wrist and each finger joint, and every rule a pose breaks |
grip | how each hand touches the rifle: with the palm, not the back of the hand; whether the palm itself holds it; how deep on each side |
arm_ranges | the research behind those limits: each joint's AAOS range, its functional range, the value checked, and the sources |
faces_eye, visible, screen | how squarely a surface faces the eye, how much of it the eye sees, where it falls on screen |
solve | searches rifle moves against goals; reports each goal and how often any sample met it |
render | a contact sheet: the player's eye and outside views, each tile labelled as a Blender view |
record_clip, load_clip | a clip from keyed poses, or from a file: .pose.json, FBX or BVH |
scan_clip | every frame against checks; the worst value, when, and the time spans that fail |
fix_clip | mends what fails and reports the scan before and after, and what no fix can reach |
save_clip | writes a clip as .pose.json bone data and as FBX for a game engine |
view_cover | how much of the player's view the arms cover: all of it, its lower left and its bottom middle |
solve_grip | searches a hand's hold: the palm on a mark along the barrel, the elbow's pole and the hand's roll; keeps holds that grip, clear, keep the arm rules and the view budget |
retarget_clip | another rig's clip on this rig, with a hand held on this gun's own hold: shared motion, the gun's own grip |
check_set | every check on a clip in one summary for a gate: the worst clearance, the frames that break a rule, the frames a hand lets go |
Every position goes in and comes out in a named frame, so no one has to guess axes:
gun: the gun bone as it stands, Unreal-style axes, cm: +X the gun's left, +Y along the barrel, +Z up (the default)arms: the arms' space, Unreal-style axes, cmview: from the eye, cm: +X right, +Y forward, +Z upTurns use the player's words: roll + turns the gun's right side up, swing + takes the muzzle left, pitch + the muzzle up. Moves (right, forward, up) are in the view.
A hand round its grip touches the rifle on the idle pose already (a finger on the trigger, fingers round the handguard). Call clearance at pose_idle for that baseline, and leave those segments out with ignore wildcards. On the built-in sample the left thumb sits 2.7 cm inside the handguard at idle. clearance measures to the rifle's surface (inside or out by ray parity), so it sees a body part inside a flat face between the mesh's corner points.
anatomy)A pose can clear the rifle and still be one no human arm can take. anatomy checks each arm against these limits:
| Joint | Rule |
|---|---|
| Shoulder | the elbow stays at least 2 cm below the shoulder while the hand works the gun |
| Elbow | a hinge, bent 5 to 150 degrees: never locked straight |
| Forearm | it carries the hand's roll (the radius turns over the ulna): pronation and supination at most 80 degrees each from thumb up, measured against the elbow's hinge plane |
| Forearm skin | on a rig with forearm twist bones, the roll spreads along the forearm: no single link (the elbow's end, each twist bone, the wrist) rolls more than 50 degrees |
| Wrist | no twist of its own; on a rig without twist bones, the hand's twist against the idle grip's at most 30 degrees |
| Wrist | within 30 degrees of the forearm's line; inside its joint range: flexion 80, extension 70, radial 20, ulnar 30 |
| Fingers | each joint curls only toward the palm: knuckle -30 to 100, middle joint -5 to 110, end joint -10 to 90 |
| Fingers | each finger stays in its own plane: the middle joint at most 15 degrees off its hinge, the end joint at most 25 off the middle joint's plane |
| Thumb | the knuckle bends -10 to 60 and the end joint -15 to 90, across the palm; the base spreads at most 80 from the index metacarpal and sits at most 20 behind the palm |
The wrist and elbow ranges are the AAOS normal values, from the AAOS 1965 table as reprinted in Greene and Heckman 1994. Other tables differ, by 10 to 25 degrees for the fingers and thumb. The 30 degree wrist line, the 5 degree elbow minimum and the elbow under the shoulder are working rules for this game's look of a hand on a gun, not joint limits. The wrist rule is stricter than daily tasks: Ryu 1991 found daily tasks use up to 60 degrees of extension and 40 of ulnar deviation. The finger limits allow 10 more flexion than AAOS at the knuckle and the middle joint; docs/ANATOMY.md says why the defaults stay that way. It gives each joint's standard and functional range, the value checked, and the sources (AAOS; Eaton; Morrey 1981; Palmer 1985; Ryu 1991; Hume 1990; Bain 2015; Soucie 2011). arm_ranges returns the same data to a model.
The anatomy reply lists, for each arm, the elbow's height under the shoulder, the elbow's bend, the wrist's bend split into flexion and radial deviation, the wrist's twist, each finger joint's curl and twist, and bad: every rule the pose breaks. Each rule reads the value as reported: angles to the degree, the elbow's height to 0.1 cm. A rig's limits, finger_limits and thumb_limits entries in rigs.json override any value. solve takes {"type": "anatomy"} as a goal.
move_gun, reach and fix_clip place hands with a turn. They move the hand's twist into the forearm, so the wrist joint only bends: a 60 degree rifle roll with the hands kept reads no wrist twist.
Fix a broken rule by moving the rifle, the grip or the elbow's pole. Do not bend a joint further.
The sample rig's idle grip breaks the wrist rule: the left wrist bends 44 degrees off the forearm and the right 58. fix_clip with an anatomy check brings the left to 29. It leaves the right at 58: every turn that mends it puts the rifle inside the back of the palm, so that hand needs a new grip or elbow, not a wrist turn.
grip)A hand holds the rifle with its palm and the palm sides of its fingers. clearance is usually run with the palms and fingers left out, since a grip touches the rifle there. That also hides a hand on the wrong side. grip checks the contact itself, for each hand:
| Rule | Default |
|---|---|
A hand on the rifle faces it with the palm, not the back (palm_faces_rifle above 0) | within hold_within_cm 1.0 |
A hand holding the rifle has its palm on it, not only a fingertip (palm_gap_cm) | palm_within_cm 1.5 |
| The rifle stays out of the back of the hand and the back of each finger | back_max_cm 0.1 |
| The palm side may press in a little: the capsules are rounder than a palm | palm_max_cm 1.0 |
Each finger segment's palm side is the side it curls toward. The thumb's pad faces sideways, so its contacts count toward the palm side's depth only. The reply gives each hand's touching (some part within hold_within_cm), holding (touching, the palm facing the rifle and its surface within palm_within_cm), palm_gap_cm, palm_faces_rifle, palm_contact_cm, back_contact_cm, where the back contact is, and bad. With hold true, a hand that is not holding breaks a rule.
A hand meant to hold a part (a magazine, a grip) must also pinch it: with grasp true, the thumb and a finger must touch it (skin within contact_cm, 0.3) from opposite sides, their directions from its surface at least 180 - 2 atan(friction) degrees apart (127 at friction 0.5). The reply gives grasping, grasp_opposition_deg and digits_touching. A hand resting on the rifle, or one that hooks a handle, is not meant to pinch: leave grasp off. solve takes {"type": "grip"} as a goal and scan_clip as a check. On the sample rig, a hand turned 180 degrees about its forearm fails it. So does the idle grip: the left thumb sits 2.8 cm inside the handguard, the right palm presses 1.2 cm into the pistol grip, and the trigger finger's back sits 0.8 cm inside the trigger guard. The sample stays as it is, so the benchmark's numbers keep their meaning.
scan_clip plays a clip frame by frame and runs checks on each frame. The checks are the solver's goals (clearance, anatomy, grip, faces_eye, visible, on_screen, barrel) and three more:
contact: a point of the hand on its mark, such as a fingertip on the charging handle (a, b, max_cm只显示了开头部分;其余内容请在仓库中阅读