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)
Video, voice, AI agent and SIP calls: create rooms, place calls, read recordings and usage.
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。
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 …”。
适用于网页版、桌面版和手机版 Claude:
https://mcp.mediasfu.com/mcp打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"sdk-tools": {
"command": "npx",
"args": [
"-y",
"@mediasfu/mcp-sdk-tools"
]
}
}
}在终端中运行这条命令
claude mcp add --transport http sdk-tools https://mcp.mediasfu.com/mcpclaude mcp add sdk-tools -- npx -y @mediasfu/mcp-sdk-tools粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"sdk-tools": {
"url": "https://mcp.mediasfu.com/mcp"
}
}
}粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"sdk-tools": {
"command": "npx",
"args": [
"-y",
"@mediasfu/mcp-sdk-tools"
]
}
}
}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": {
"sdk-tools": {
"type": "http",
"url": "https://mcp.mediasfu.com/mcp"
}
}
}粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"sdk-tools": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@mediasfu/mcp-sdk-tools"
]
}
}
}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。
ChatGPT 只能连接互联网上的服务器:
https://mcp.mediasfu.com/mcp菜单名称可能因套餐和版本不同而略有差异。
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。
我们还没有读取这个服务器的工具列表;我们会轮流检查各个端点。
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 MediaSFU 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
尚未检查;我们会轮流检查各个端点
尚未检查;我们会轮流检查各个端点
尚未检查;我们会在检查端点时读取工具列表
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。
两种方式都可以:安装在你的电脑上,或者连接云端版本。
GitHub 仓库最后更新于–,最新版本(1.2.0)于20天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,所以接受远程 MCP 服务器的应用也可以使用,例如开启开发者模式的 ChatGPT。
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。
The official MediaSFU MCP toolkit helps developers and MCP-capable agents plan, scaffold, diagnose, and harden MediaSFU frontend and backend integrations.
Run the stdio server directly with npm:
npx -y @mediasfu/mcp-sdk-tools
For repeatable MCP client configuration, pin the supported major version:
{
"mcpServers": { "mediasfu": { "command": "npx", "args": ["-y", "@mediasfu/mcp-sdk-tools@1"] } } }
On Windows, use npx.cmd if the MCP client does not resolve the npm shim. You can also install globally and run the explicit executable:
npm install --global @mediasfu/mcp-sdk-tools@1
mediasfu-mcp
The mediasfu-mcp-http executable starts the optional local Streamable HTTP transport. See LOCAL_MCP_SETUP.md for client examples.
mediasfu-mcp-account lets your assistant create and end rooms, place AI-agent and SIP calls, list recordings, set your room webhook and read balance and usage, using your MediaSFU API key. It runs locally over stdio; the key stays in your MCP client's environment, is sent only to https://mediasfu.com, and is redacted from every tool result.
{
"mcpServers": { "mediasfu-account": { "command": "npx", "args": ["-y", "-p", "@mediasfu/mcp-sdk-tools@1", "mediasfu-mcp-account"], "env": { "MEDIASFU_API_USERNAME": " ", "MEDIASFU_API_KEY": " " } } } }
Get both values at mediasfu.com/api-keys. Start with a sandbox key: rooms beginning with s are sandbox, p are production.
| Area | Tools |
|---|---|
| Rooms | mediasfu_create_room, mediasfu_join_room, mediasfu_list_rooms, mediasfu_get_room, mediasfu_room_stats, mediasfu_delete_room (ends the room) |
| Agent and phone calls | mediasfu_initiate_call, mediasfu_start_call_agent, mediasfu_stop_call_agent, mediasfu_switch_call_source, mediasfu_end_call, mediasfu_list_calls, mediasfu_get_call_state, mediasfu_get_call_summary, mediasfu_list_sip_numbers, and hold, play, recording and callback controls |
| Recordings | mediasfu_list_recordings |
| Webhooks | mediasfu_get_webhook, mediasfu_set_webhook |
| Usage | mediasfu_get_balance, mediasfu_get_room_usage |
| Defaults | mediasfu_create_event_settings, mediasfu_update_event_settings |
Read tools run immediately. Anything that creates, changes, calls or ends returns confirmation_required with a preview until the assistant calls it again with confirm: true, so you approve every billable or destructive step.
The default public surface exposes 159 integration tools. Thirty-three documentation-build and parity tools are internal; set MCP_INCLUDE_INTERNAL_TOOLS=1 only in a trusted local maintainer workspace to expose the full 192-tool surface.
Every SDK provides:
sdk.recommendapp.scaffoldintegration.planenv.preflightroom.bootstrapfeature.mapruntime.diagnosefix.suggestapi.reference.searchroom.flow.explainui.mode.recommendui.overrides.guidesecurity.proxy.roomsThe shared surface adds production patterns derived from MediaSFU's headless, widget, telephony, and AI call-control integrations:
shared::frontend.architecture.planshared::headless.integration.planshared::widget.integration.planshared::telephony.call-control.planshared::solution.capsule.planshared::external-media.integration.planshared::participant-control.integration.planshared::room.lifecycle.planshared::embedded.layout.planshared::room.authority.planshared::product.pattern.planshared::custom-recording.scene.planshared::runtime.readiness.diagnoseshared::lifecycle.cleanup.auditshared::credential.broker.planshared::backend.integration.guideThe widget planner distinguishes the six standalone custom elements, plain script delivery, modular npm imports, and the optional React/headless entries. It also returns the reviewed package state so package publication and hosted delivery are never mistaken for complete live-runtime evidence.
Tool names use sdkId::toolId, for example reactjs::integration.plan.
sdk-registry.json records the detected package name/version, manifest and reference hashes, and per-SDK evidence topics. feature.map returns this as sdkRelease and capabilityEvidence.
Evidence status is intentionally conservative:
documented means the capability is evidenced in the bundled SDK reference.not-evidenced means the bundled reference does not prove it; it does not claim the SDK cannot support it.npm run registry:check fails when a manifest, bundled reference, live package version, canonical package path, or evidence profile drifts. It also fails when a discoverable MediaSFU SDK workspace is not registered. Maintainers refresh reviewed changes with npm run registry:write.
feature.map also returns the canonical language-neutral operation IDs, evidence status vocabulary, exact SDK coverage identity, and security boundary. The MCP registry stores one hash-bound catalog reference and one compact hash-bound runtime-contract reference. The latter records the runtime registry schema, required stable contract IDs, complete contract-ID list, source path, and SHA-256 without copying the per-SDK evidence rows. Custom recording scenes are described in the canonical custom recording guide; the MCP surface exposes the ordinary recording lifecycle and points adopters to that guide for the portable scene contract and server-owned completion rules. The canonical product-pattern index and starter catalog link runnable Familiar Calls, Live Auction, Watch Together, Agents, VOIP, and SpacesTek references to their independently qualified platform evidence. The lifecycle, layout, authority, product-pattern, and custom-recording planners expose those contracts without treating application composition or shared-core exports as cross-SDK proof. Run npm run catalog:check locally to detect operation, coverage, security, or runtime-contract drift.
Scaffolding is a dry run unless apply: true is explicit. Apply mode:
projectRoot, defaulting to the MCP process working directory;outputDir, defaulting to mediasfu-generated/sdkId;overwrite: true;MEDIASFU_INTEGRATION.md with the detected SDK release and runtime checklist;ReactJS emits production-pattern TypeScript/React starters based on the live MediaSFU frontend's headless runtime model. Other SDKs emit version-aware implementation recipes where the package API has not been compile-verified by this Node release process. This avoids presenting speculative source as compile-ready code.
Example:
node ./scripts/mcp-engine.mjs run reactjs app.scaffold --input '{"apply":true,"projectRoot":"/path/to/app","outputDir":"src/mediasfu"}'
Obtain scoped room/session material from an authenticated backend. Never put a long-lived MediaSFU API key in browser storage, mobile preferences, source code, logs, or a shipped desktop/mobile/game binary.
npm install
npm run validate npm run registry:check npm run mcp:server:selftest npm run mcp:http:selftest npm run release:check
Useful examples:
node ./scripts/mcp-engine.mjs list reactjs
node ./scripts/mcp-engine.mjs run reactjs integration.plan --input '{"appType":"meeting"}' node ./scripts/mcp-engine.mjs run reactjs api.reference.search --input '{"query":"create room"}' node ./scripts/mcp-engine.mjs run reactjs feature.map --input '{"requestedFeatures":["conference","screen-share"]}' node ./scripts/mcp-engine.mjs run shared frontend.architecture.plan --input '{"mode":"auto","needsWidget":true}'
Stdio entry point: scripts/mcp-stdio-server.mjs.
Streamable HTTP entry point: scripts/mcp-http-server-v2.mjs. It exposes public read-only tools at /mcp and scoped MediaSFU account actions at /mcp/actions.
The stdio and public HTTP tool surfaces are read-only by default. Local filesystem/command side effects require MCP_ALLOW_LOCAL_SIDE_EFFECTS=1 and must never be enabled on a shared endpoint.
The hosted /mcp endpoint is intentionally free of authentication and permanently read-only. The separate /mcp/actions endpoint requires Authorization: Bearer : , validates the key with MediaSFU, filters tools by key scope, and confirms side effects. See server/README.md.
Use shared::backend.integration.guide for /v1/rooms, event settings, and disposable-key contracts. Never send credentials to the public/stdio tools. The action endpoint accepts only a disposable credential in the exact documented Authorization header and never exposes it to tools or logs.
npm run release:check validates:
Run npm run pack:dry-run and npm audit before publication. Publishing is intentionally a separate maintainer action.
Additional public setup and deployment notes are in LOCAL_MCP_SETUP.md and server/README.md.
MediaSFU MCP SDK Tools is released under the MIT License.