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)
Transcode/conform/splice video, convert docs, transcribe audio for AI agents. Free $1 trial.
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。
BOTVERSE_API_KEY, BOTVERSE_CONNECTOR_URL标为机密的值是你账户的钥匙。千万不要分享给别人,也不要粘贴到聊天里。
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": {
"botverse": {
"command": "npx",
"args": [
"-y",
"botverse-mcp"
],
"env": {
"BOTVERSE_API_KEY": "your-value",
"BOTVERSE_CONNECTOR_URL": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add botverse --env BOTVERSE_API_KEY=your-value --env BOTVERSE_CONNECTOR_URL=your-value -- npx -y botverse-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": {
"botverse": {
"command": "npx",
"args": [
"-y",
"botverse-mcp"
],
"env": {
"BOTVERSE_API_KEY": "your-value",
"BOTVERSE_CONNECTOR_URL": "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": {
"botverse": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"botverse-mcp"
],
"env": {
"BOTVERSE_API_KEY": "your-value",
"BOTVERSE_CONNECTOR_URL": "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。
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 MkTurner74 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。
你需要填写:BOTVERSE_API_KEY, BOTVERSE_CONNECTOR_URL
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(1.5.1)于2个月前进入注册中心。
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 Node.js。
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。
MCP server and command-line tool for Botverse — video transcoding and document conversion for AI agents and the humans who configure them.
Two ways to use it: an MCP server for your AI agents, and a `botverse` CLI for the shell — evaluation, CI/CD, cron, scripts, and local coding agents. No AWS. No FFmpeg. No infrastructure.
{
"mcpServers": { "botverse": { "command": "npx", "args": ["-y", "botverse-mcp"], "env": { "BOTVERSE_API_KEY": "bv_live_..." } } } }
Or with a connector URL (recommended for claude.ai):
{
"mcpServers": { "botverse": { "command": "npx", "args": ["-y", "botverse-mcp"], "env": { "BOTVERSE_CONNECTOR_URL": "https://botverse.cloud/mcp?token=bv_sess_..." } } } }
botverse)The same package ships a botverse CLI for the shell — it reads files from disk and streams them straight to the API (no content goes through an LLM), so it's the fast path for evaluation, automation, and local coding agents.
export BOTVERSE_API_KEY=bv_live_… # or BOTVERSE_CONNECTOR_URL=…?token=bv_sess_…
npx botverse convert report.md --to pdf npx botverse convert *.md --to docx,pdf -o ./out npx botverse transcode clip.mov --to mp4 -o ./out npx botverse transcribe call.mp4 --to docx --attendees "Sarah Chen,Mike Torres" npx botverse conform video.mp4 audio.wav --to mp4 --method speed_conform --target-framerate 25 npx botverse balance
Each job uploads → polls → downloads the finished file to -o (default: current dir). Globs and multiple --to formats run as a batch.
Sandbox note: the CLI needs outbound network to
botverse.cloudand Botverse's file storage host, so it does
not run inside sandboxed agent environments (claude.ai / Claude Desktop), whose
egress is allowlisted. There, use the MCP tools (e.g.
convert_content) instead.
| Tool | Description |
|---|---|
get_upload_url | Get a presigned URL to upload a file for use with the _media/_file/_video (object-key-based) tools |
transcode_from_url | Transcode video from a public URL |
transcode_video | Transcode an uploaded video file |
conform_from_url | Mux a separate video + audio source (public URLs) into one output |
conform_media | Mux an uploaded video + audio source into one output |
conform_splice_from_url | Concatenate video/image segments (public URLs) — slates, bumpers, end cards, inserts, joined clips |
conform_splice_media | Concatenate uploaded video/image segments — same use cases |
convert_content | Convert document content inline (up to 4 MB; sandbox-safe) |
convert_from_url | Convert a document from a public URL |
convert_file | Convert an uploaded document |
submit_workflow | Submit a multi-step BWDL workflow chaining several of the above tools together, with dependency ordering and parallel branches |
get_workflow_status | Poll a workflow (and its per-step status) until it reaches a terminal state |
cancel_workflow | Cancel an in-progress workflow; already-completed steps are billed, the rest are not |
get_job_status | Poll a job until complete |
get_download_url | Get the signed download URL |
get_wallet_balance | Check wallet balance |
submit_workflow chains multiple Botverse tools (transcode, convert, transcribe, conform, splice) into one server-side job — e.g. transcribe → clip extraction → delivery — instead of your agent making each call and polling each one individually.
workflow_id and a steps array. Each step has an id, a tool (any MCP tool name), an inputs object, and an optional depends_on array of prior step ids.depends_on run in parallel."$.steps. .output_key", and a workflow-level parameter with "$.params. " — no other template syntax is supported.submit_workflow, poll with get_workflow_status every 5–10 seconds until the status is COMPLETED, FAILED, PARTIALLY_FAILED, or CANCELLED, and stop early with cancel_workflow if needed (you're only billed for steps that already completed).Example — a two-step conversion chain (URL → DOCX → PDF):
{
"workflow_id": "md-to-pdf-via-docx", "steps": [ { "id": "to_docx", "tool": "convert_from_url", "inputs": { "source_url": "https://example.com/report.md", "output_format": "docx" } }, { "id": "to_pdf", "tool": "convert_file", "depends_on": ["to_docx"], "inputs": { "object_key": "$.steps.to_docx.output_key", "output_format": "pdf" } } ] }
Credits never expire. Full pricing →