Figma Context MCP
Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.
Description from the maker (original English)
Literature, Zotero, PDF, citation, materials, and scientific image tools for research agents.
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.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"omnischolar": {
"command": "uvx",
"args": [
"luffysolution-omnischolar",
"mcp"
]
}
}
}Run this in your terminal
claude mcp add omnischolar -- uvx luffysolution-omnischolar mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"omnischolar": {
"command": "uvx",
"args": [
"luffysolution-omnischolar",
"mcp"
]
}
}
}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": {
"omnischolar": {
"type": "stdio",
"command": "uvx",
"args": [
"luffysolution-omnischolar",
"mcp"
]
}
}
}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 one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
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 registry name was verified with the GitHub account luffysolution-svg, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 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.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (0.1.0) reached the registry 2 months ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Python (uv) on your computer.
In the same category: Figma Context MCP, Claude Real Video, Figma MCP Server
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
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.
Figma’s official server gives AI your design data so it can turn designs into code or describe them accurately. Connects to Figma’s cloud.
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.
简体中文 | English
OmniScholar 通过本地 Python MCP 服务,为 Codex、Claude Code、Cursor、OpenCode、Hermes 和 Pi 提供文献检索、Zotero 读取、PDF 解析、引用处理、材料数据和科研绘图工具。
它可以把在线文献记录与 Zotero 笔记放在一起处理,将经你确认的 PDF 交给 MinerU 解析,再把 Markdown 保存到普通文件夹或 Obsidian Vault。Zotero 全程只读。
.conflicts/source/OmniScholar 共提供 39 个工具,完整列表见工具目录。
安装与部署
需要 Python 3.11 或更高版本。普通 Python 命令任选一种方式安装:
uv tool install luffysolution-omnischolar
pipx install luffysolution-omnischolar
python -m pip install luffysolution-omnischolar
检查、更新和卸载:
omnischolar --version
omnischolar doctor --json uv tool upgrade luffysolution-omnischolar uv tool uninstall luffysolution-omnischolar
如果希望用一条命令强制刷新并重装最新版:
uv tool install --reinstall luffysolution-omnischolar
codex plugin marketplace add luffysolution-svg/omnischolar --ref main
codex plugin add omnischolar@omnischolar
codex plugin marketplace upgrade omnischolar codex plugin remove omnischolar@omnischolar codex plugin add omnischolar@omnischolar
ChatGPT 桌面应用中重启应用后打开 Plugins,选择 OmniScholar 并安装或启用;Codex CLI 可运行 /plugins 浏览插件。插件已经包含 Skills,并通过下面的命令启动 PyPI 最新 MCP:
uvx --refresh-package luffysolution-omnischolar --from luffysolution-omnischolar@latest omnischolar mcp
在 Claude Code 会话中运行:
/plugin marketplace add luffysolution-svg/omnischolar
/plugin install omnischolar@omnischolar
普通终端也可以运行:
claude plugin marketplace add luffysolution-svg/omnischolar
claude plugin install omnischolar@omnischolar --scope user claude plugin update omnischolar@omnischolar --scope user
pi install npm:@luffysolution/omnischolar-pi
pi update npm:@luffysolution/omnischolar-pi pi remove npm:@luffysolution/omnischolar-pi
omnischolar install --dry-run claude
omnischolar install claude omnischolar update claude omnischolar uninstall claude
也可以使用官方 Skills CLI 单独安装 Skills;插件已经包含这些 Skills,通常不需要重复安装:
npx skills add luffysolution-svg/omnischolar --skill '*' --agent codex --global --yes
npx skills update --global --yes npx skills remove --skill '*' --agent codex --global --yes
完整的各 Agent 路径、项目级安装和故障排查见安装说明。
可以将下面的提示词作为 Agent 的项目级指令或系统提示词基础:
你是我的科研助理,使用 OmniScholar 完成文献检索、Zotero 阅读、PDF 解析、引用核对和科研资料整理。检索时优先使用可靠的学术来源,核对 DOI 与书目信息,并明确区分原文证据、推断和不确定内容。Zotero 只允许读取,禁止修改。上传 PDF、参考图或发起可能收费的请求前必须先征得我的确认;MinerU 只有在我确认后才能上传文件。将确认后的文献笔记和生成文件保存到配置的输出目录,保留已有手工修改,并报告最终文件路径。生成的科研图片只能作为示意图,不能当作实验数据或科研证据。
首次启动 MCP 或运行安装器时,如果没有可发现的配置,OmniScholar 会创建用户级 omnischolar.config.json 模板。模板中的服务默认处于启用状态;填写 API key 后即可使用对应服务,没有凭据的服务不会自动发起请求。API key 可以直接填写到 apiKey,也可以用 apiKeyEnv 指定环境变量。
填写对应 API key 并启用服务后,即可直接使用 Ai4Scholar、图片生成、MinerU 和参考图上传。
根目录的 mcp.json 是可直接复制到支持 MCP 的 Agent 中的 stdio 示例,内容如下:
{
"mcpServers": { "omnischolar": { "type": "stdio", "command": "uvx", "args": ["--refresh-package", "luffysolution-omnischolar", "--from", "luffysolution-omnischolar@latest", "omnischolar", "mcp"] } } }
mcp.json 只负责启动 MCP,不保存 API key;服务凭据和 Obsidian 输出位置填写在 omnischolar.config.example.json 对应字段中,可执行 omnischolar config init 创建实际配置。插件内部使用的配置文件是 .mcp.json。MinerU 原文与 Zotero 阅读记录都会写入书目信息 frontmatter,解析图片始终以 Zotero key 开头;文件夹、Markdown 文件和图片命名可通过 output 区块自定义,详见文献与输出配置。
查找 5 篇关于固态电池界面的近期综述,按 DOI 去重,并给出开放获取版本。
在我的 Zotero 中找到这个 DOI,汇总笔记和批注,不要修改 Zotero。
我确认上传后,用 MinerU 解析这份 PDF,并把阅读笔记保存到 Obsidian Vault。
查询 Materials Project 中稳定的 Li-Fe-P-O 材料,将选中的记录导出为 CSV 和 CIF。
为这个机理绘制带标签的示意图。图片只是草稿,不得写成实验数据。
OmniScholar 使用 MIT License 开源。可以在 GitHub Issues 提交问题,或发送邮件到 LuffySolution@gmail.com。报告问题前,请删除 API key、签名 URL、私人论文内容和个人 Zotero 数据。
第三方服务和数据遵循各自的条款与许可证,详见 THIRD_PARTY_NOTICES.md。