Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
作者提供的说明(英文原文)
MCP server for searching Pexels stock photos, videos, and curated collections.
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。
PEXELS_API_KEY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": {
"pexels": {
"command": "npx",
"args": [
"-y",
"mcp-pexels"
],
"env": {
"PEXELS_API_KEY": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add pexels --env PEXELS_API_KEY=your-value -- npx -y mcp-pexels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": {
"pexels": {
"command": "npx",
"args": [
"-y",
"mcp-pexels"
],
"env": {
"PEXELS_API_KEY": "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": {
"pexels": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"mcp-pexels"
],
"env": {
"PEXELS_API_KEY": "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6日
注册名称已通过 GitHub 账户 developer-ishan 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:PEXELS_API_KEY
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(1.0.2)于6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:Spec Driven Development, Remote Desktop Commander, debuff
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
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.
Let coding agents play, test and tune your 2D web game: live state, explained errors, replays, fuzz.
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。
A [Model Context Protocol](https://modelcontextprotocol.io) server that exposes the [Pexels API](https://www.pexels.com/api/) — free stock photos, videos, and curated collections — as MCP tools that any compatible AI client (Claude Desktop, Claude Code, Cursor, Cline, Continue, etc.) can call directly from a chat.
📦 npm: mcp-pexels · 🏷 Latest release: v1.0.0 · 💻 Source: developer-ishan/mcp-pexels
Photos & videos provided by Pexels.
{
"mcpServers": { "pexels": { "command": "npx", "args": ["-y", "mcp-pexels"], "env": { "PEXELS_API_KEY": "your_key_here" } } } }
Paste into your MCP client's config, restart, and the nine pexels_* tools are live. Get a free key at https://www.pexels.com/api/.
Once mcp-pexels is connected to an AI client, the agent can pull royalty-free photos and videos straight into its workflow. A few concrete uses:
pexels_popular_videos with size and duration filters.color: "orange".lorem-pixel boxes.Because every response includes a _rateLimit object, the agent can self-throttle and respect the Pexels free-tier quota (200 req/hour, 20 000/month).
| Domain | Tool | What it does |
|---|---|---|
| Photos | pexels_search_photos | Search photos by query with orientation / size / color / locale filters. |
| Photos | pexels_curated_photos | Fetch the Pexels team's real-time curated photo feed. |
| Photos | pexels_get_photo | Retrieve a single photo by its numeric id. |
| Videos | pexels_search_videos | Search videos by query with orientation / size / locale filters. |
| Videos | pexels_popular_videos | Fetch popular videos with optional width / height / duration constraints. |
| Videos | pexels_get_video | Retrieve a single video by its numeric id. |
| Collections | pexels_featured_collections | List Pexels featured collections. |
| Collections | pexels_my_collections | List the authenticated user's own collections. |
| Collections | pexels_collection_media | Retrieve the photos and videos inside a specific collection. |
Each tool response is the raw Pexels JSON merged with a top-level _rateLimit field exposing limit, remaining, and reset (UNIX timestamp).
See docs/tools/ for per-tool parameter tables and example payloads.
All paths below use npx -y mcp-pexels — no global install required. Replace your_key_here with a real Pexels API key.
Option 1 — one-click `.mcpb` install (recommended). Download the latest mcp-pexels-*.mcpb from the Releases page, double-click the file, paste your Pexels API key when Claude Desktop prompts, and click Install.
Option 2 — manual JSON config. Edit claude_desktop_config.json:
~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.json~/.config/Claude/claude_desktop_config.json{
"mcpServers": { "pexels": { "command": "npx", "args": ["-y", "mcp-pexels"], "env": { "PEXELS_API_KEY": "your_key_here" } } } }
Restart Claude Desktop.
claude mcp add pexels -e PEXELS_API_KEY=your_key_here -- npx -y mcp-pexels
Or edit ~/.claude.json directly and add the same mcpServers block as above.
Edit ~/.cursor/mcp.json (global) or .cursor/mcp.json (per-project):
{
"mcpServers": { "pexels": { "command": "npx", "args": ["-y", "mcp-pexels"], "env": { "PEXELS_API_KEY": "your_key_here" } } } }
Open the Cline extension settings → MCP Servers → Edit Settings. Add:
{
"mcpServers": { "pexels": { "command": "npx", "args": ["-y", "mcp-pexels"], "env": { "PEXELS_API_KEY": "your_key_here" } } } }
In ~/.continue/config.json:
{
"experimental": { "modelContextProtocolServers": [ { "transport": { "type": "stdio", "command": "npx", "args": ["-y", "mcp-pexels"], "env": { "PEXELS_API_KEY": "your_key_here" } } } ] } }
If your client supports stdio MCP servers it just needs command, args, and env. Use the same shape as Cursor / Claude Desktop above. For inspector / debugging:
export PEXELS_API_KEY=your_key_here
npx -y @modelcontextprotocol/inspector npx -y mcp-pexels
This opens a browser UI where you can call each tool interactively.
Once connected, try prompts like:
The agent will pick the appropriate tool, send the right parameters, and include photographer/videographer credit as part of its answer.
| mcp-pexels | Raw Pexels REST API | Image-only general MCP servers | |
|---|---|---|---|
| Photos | ✅ | ✅ | varies |
| Videos | ✅ | ✅ | usually ❌ |
| Collections | ✅ | ✅ | ❌ |
| Rate-limit headers exposed to agent | ✅ | ❌ (raw headers, agent must parse) | ❌ |
| Zod-validated input | ✅ | ❌ | varies |
npx-installable, zero config | ✅ | ❌ | varies |
| Type-safe TS source | ✅ | n/a | varies |
| MIT-licensed | ✅ | n/a | varies |
If you only need photos and you already have a generic image MCP server wired up, that may be enough. If you want first-class video and collection support with rate-limit awareness, this is purpose-built for it.
Sign up at https://www.pexels.com/api/ — keys are issued instantly and the free tier allows 200 requests/hour and 20 000 requests/month.
No. The Pexels API is free, the npm package is free (MIT), and mcp-pexels itself does not call any paid service.
No — the server is a thin wrapper over the Pexels HTTPS API and requires network access.
Yes, per the Pexels license, but you must attribute the platform and (when possible) the photographer. See Attribution.
Claude.ai's web product doesn't yet support stdio MCP servers — only Claude Desktop, Claude Code, and the API do. Anthropic is rolling out browser MCP support, so this should change.
No. Run it locally via npx. Because Pexels API keys are per-user, hosting a shared instance doesn't make sense.
npx always fetches the latest published version. If you've installed globally, run npm update -g mcp-pexels.
The Pexels API surface is fully implemented (9/9 endpoints as of Pexels API v1). New endpoints will be added via PR — see Contributing.
@modelcontextprotocol/inspector?Yes:
export PEXELS_API_KEY=your_key_here
npx -y @modelcontextprotocol/inspector npx -y mcp-pexels
Every tool response includes a _rateLimit object with limit, remaining, and reset (UNIX timestamp). The agent can read this and self-throttle. If Pexels returns 429, the server surfaces it as a PexelsApiError so the agent sees the failure.
It is read from the PEXELS_API_KEY env var on the local process. It never leaves your machine except in Authorization headers to api.pexels.com. Nothing is logged.
fetch and --env-file)git clone https://github.com/developer-ishan/mcp-pexels.git
cd mcp-pexels npm install echo "PEXELS_API_KEY=your_key_here" > .env
npm test # 42 mocked vitest cases, no network npm run build # tsc → dist/ npm run dev # tsx watch npm run test:watch # vitest in watch mode npm start # node --env-file=.env dist/index.js
src/
├── index.ts # MCP server entrypoint (stdio) ├── http/ │ ├── client.ts # PexelsClient (injectable fetch for tests) │ └── types.ts # PexelsApiError, RateLimit, PexelsResponse ├── tools/ │ ├── index.ts # composes the three domain factories │ ├── photos.ts # 3 photo tools │ ├── videos.ts # 3 video tools │ └── collections.ts # 3 collection tools └── types/ ├── tool.ts # defineTool helper + ToolDefinition ├── photos.ts ├──
只显示了开头部分;其余内容请在仓库中阅读