Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Render Spine 3.8 skeleton animations to PNG frames or GIF. Pay per call with points.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
AuthorizationValues marked secret are keys to your account. Never share them or paste them into a chat.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
This address needs a key in a request header, which the add-connector menu cannot set. Use Claude Code, Cursor or VS Code instead.
Run this in your terminal
claude mcp add --transport http spine-render https://lain42.top/studio/render/mcp-server/mcp --header 'Authorization: your-value'Fill in the empty values before running it.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"spine-render": {
"url": "https://lain42.top/studio/render/mcp-server/mcp",
"headers": {
"Authorization": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"spine-render": {
"type": "http",
"url": "https://lain42.top/studio/render/mcp-server/mcp",
"headers": {
"Authorization": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This address needs a key in a request header, which the add-connector menu cannot set. Use Claude Code, Cursor or VS Code instead.
Your choice stays on this device in a cookie; no account needed.
Authorization secret required HTTP headerThese settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
We have not read this server’s tool list yet; we check endpoints in rotation.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026
The publisher (lain42.top) is not the repo owner (lilyco-42); someone else may have listed it
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Not checked yet; we check endpoints in rotation
Not checked yet; we check endpoints in rotation
Not checked yet; we read the tool list when we check the endpoint
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 0 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
You need to fill in: Authorization
It runs in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
The GitHub repo last changed –, and the latest version (0.1.1) reached the registry 16 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.
In the same category: Spec Driven Development, Remote Desktop Commander, FlyDocs
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Spec-driven development workflow: your agent works issues, sessions and the status lifecycle.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
多模态 AI 资源流水线:一条命令产出 Minecraft 皮肤、Bedrock 模型、BGM、立绘、歌词。
Owner: lilyco-42(云枢智创数码信息科技服务工作室)
调研与决策记录在
_RESEARCH/
lyco-cli bundle --prompt 'a quiet librarian' --out out
lyco-cli bundle 整包:skin + model + bgm + portrait + lyrics + manifest
lyco-cli skin template | validate | info | quantize | generate lyco-cli bsm humanoid | validate | info | glb-info | from-glb lyco-cli bgm 背景音乐 lyco-cli lyrics 分段歌词 lyco-cli portrait 单张立绘 lyco-cli mcp 在 stdin/stdout 上跑 MCP server,给 agent 用
lyco-cli mcp 是一个 MCP server,用换行分隔的 JSON-RPC 2.0 收发。它把 12 个工具 暴露给 lilyco_agent / Claude Code / Cursor:skin_template、skin_validate、 skin_quantize、model_humanoid、model_validate、glb_info、model_from_glb、 lyrics_generate、lyrics_validate、bgm_generate、portrait_generate、bundle。
手动试一次:
printf '%s\n' \
'{"jsonrpc":"2.0","id":1,"method":"initialize"}' \ '{"jsonrpc":"2.0","method":"notifications/initialized"}' \ '{"jsonrpc":"2.0","id":2,"method":"tools/list"}' \ | lyco-cli mcp
lyco-ai-toolkit/
+-- crates/ | +-- lyco-cli/ 统一入口(clap) | +-- lyco-mc-skin/ F1 64x64 box-UV、调色板量化、皮肤校验 | +-- lyco-bsm/ F2/F3 Bedrock 几何、玩家模型、GLB 解析、体素化转换 | +-- lyco-audio/ F6 WAV 编解码、生成后端(stub + 子进程) | +-- lyco-image/ F7 程序化立绘、生成后端 | +-- lyco-lyrics/ F8 歌词解析与结构校验、生成后端 | +-- lyco-bundle/ S5 编排 + 自描述 manifest | +-- lyco-mcp/ F9 MCP server(JSON-RPC over stdio) +-- _RESEARCH/ lyco skill 预研报告(00-04) +-- scripts/ 测试夹具生成器(造 GLB)
stub 后端在 CLI、manifest 的 placeholder 字段和 notes 里三处标注,一个 bundle 永远不会看起来像五次真实生成。--backend 指过去。皮肤生成真的能跑 —— 不需要本机有显卡:
lyco-cli skin generate --backend kaggle --owner <you> --slug lyco-skin-gen --seeds 7,42
它把 Rust 生成的笔记本推到 Kaggle,在免费的 Tesla T4 上跑 AliceKJ/BLOCKv0.6, 轮询到结束,拉回产物,然后在本机做 overlay 修复、结构校验和人形预览。
分工是刻意的:Kaggle 只做它唯一不可替代的事(GPU 推理),UV 知识和修复逻辑归 Rust。 生成的笔记本里没有 UV 表,CI 会断言这一点。
其余需要模型的部分(音频引擎、图像引擎、LLM)仍是 --backend '<命令行>' 子进程边界。
lyco-cli spine info model.atlas # 页 / region / 是否声明 size、pma
lyco-cli spine normalize model.atlas # 从 PNG 头补/修 size,幂等 lyco-cli spine version model.skel # 读出需要的 Spine 版本
lyco-spine-render 能把 Spine 骨架摆姿势并在 CPU 上画成 PNG(describe / render --animation NAME)。已用真实方舟数据验证:Spine 3.8.99、52 mesh、508 三角形。
但它不随本仓库发布二进制,原因很具体:
windows-binary 只发纯 MIT 的 lyco-cli.exe要拿到这个二进制,用仓库里的 build from source workflow(workflow_dispatch): 你在自己的 fork 里触发,在你自己的授权下构建,产物只进你这次 run。
它的输入:
target —— 默认 lyco-spine-render,也可选 lyco-cli 或 bothrunner —— 默认 windows-latest,或 ubuntu-latestrusty_spine3.8)spine_lib 和 spine_rev 是真的生效的:workflow 会改写 crates/lyco-spine-render/Cargo.toml 里那一行再开始构建,所以你可以拿它试别的运行时。 运行时地址、revision、许可链接会在构建开头打印,并且参与缓存 key, 换 revision 不会误用旧产物。
缓存:默认 CI 和这个 workflow 都缓存两层 —— ~/.cargo/git/db 与 ~/.cargo/git/checkouts(Spine 运行时那个 git 依赖的 clone, 冷启动最慢的一步),以及 rust-cache 管的 target/ 增量编译。
注意:`pma` 是 Spine 4.x 的键。 往 3.8 的 atlas 里写 pma: true 会让 3.8 运行时 完全读不了那个文件 —— 实测确认(方舟素材池 561 组里 243 组带着它)。两条路都通:
lyco-spine-render 读取前把 3.8 认不了的字段剥掉(旁路写一份 临时 atlas,用完即删),561/561 全部可读可渲;lyco-cli spine normalize --strip-3-8 把剥离结果写回文件。每次 CI 跑:test → clippy -D warnings → build → 6 组冒烟测试 → fmt。 冒烟测试用外部实现交叉验证:Python 的 wave 解码我们写的 WAV、直接读 PNG 头核对尺寸、 现造 GLB 喂给转换、以及一次真实 MCP 会话。
keep-percent=12% 这个启发式对某些 seed 会整体清空残留很少的 overlay 矩形, 可能丢掉真实衣物细节;需要人眼判断是否调低调研初稿曾写「YSM/BSM 是 BlockBench 格式」——错的,已在 _RESEARCH/02-niche-knowledge.md 第五节更正: Blockbench 没有这两个格式且是 GPL-3.0;YSM 是 Yes Steve Model 模组的加密二进制; BSM 不存在。本项目落点是开放的 Bedrock geometry。
MIT