Pexels MCP Server
Enables AI models to search and retrieve photos, videos, and collections from Pexels via the Pexels API.
README
Pexels MCP Server
A Model Context Protocol (MCP) server that provides access to the Pexels API, allowing AI models to search for and retrieve photos, videos, and collections from Pexels.
Features
- Search for photos and videos by query, orientation, size, and color
- Access curated and popular content from Pexels
- Browse Pexels collections
- Get detailed information about specific photos and videos
- Access content via tools or direct URI resources
Requirements
- Node.js 18 or higher
- A Pexels API key (get one at https://www.pexels.com/api/)
Local Development
- Clone the repository
- Install dependencies
pnpm install - Build the project
pnpm build - Run in development mode
PEXELS_API_KEY=your_api_key pnpm dev
Deploying to Smithery
This MCP server is ready to be deployed to Smithery. Follow these steps:
- Add the server to Smithery or claim an existing server
- Go to the Deployments tab (only visible to authenticated owners)
- Deploy the server
- When configuring the deployment, provide your Pexels API key in the configuration settings
API Usage
The server provides the following tools:
Photo Tools
searchPhotos: Search for photos by query (use descriptive keywords for relevant results, e.g., 'Thai hotel reception', 'red sports car driving', not just 'hotel' or 'car'; combine with parameters likeorientation,size,color, andlocalefor refined results), with optional filters for orientation, size, color, locale (e.g., 'en-US', 'es-ES'), page, and results per page. Returns metadata including photo IDs and URLs, plus current API rate limit status.downloadPhoto: Fetches a specific photo by its ID and desired size (optional, defaults to 'original'). Available sizes: 'original', 'large2x', 'large', 'medium', 'small', 'portrait', 'landscape', 'tiny'. Returns a direct download link for the requested image size, suggested filename (including size), and attribution information. The AI client should use its available local tools (likecurlor PowerShell'sInvoke-WebRequest) to download the photo using the provided link.getCuratedPhotos: Retrieve a curated set of photos from Pexels, optionally paginated.getPhoto: Retrieve detailed information about a specific photo by its ID.
Video Tools
searchVideos: Search for videos by query (use descriptive keywords for relevant results, e.g., 'drone footage beach sunset', 'time lapse city traffic', not just 'beach' or 'city'; combine with parameters likeorientationandsizefor refined results), with optional filters for orientation, size, locale (e.g., 'en-US', 'es-ES'), page, and results per page. Returns metadata including video IDs and URLs, plus current API rate limit status.getPopularVideos: Retrieve a list of popular videos from Pexels, with optional filters for dimensions, duration, page, and results per page.getVideo: Retrieve detailed information about a specific video by its ID.downloadVideo: Fetches a specific video by its ID and preferred quality (hd/sd). Returns a direct download link, suggested filename, and attribution information. The AI client should use its available local tools (likecurlor PowerShell'sInvoke-WebRequest) to download the video using the provided link.
Collection Tools
getFeaturedCollections: Retrieve a list of featured collections from Pexels, optionally paginated.: (Commented out in code) Requires OAuth 2.0 authentication, not supported by this server.getMyCollectionsgetCollectionMedia: Retrieve media items (photos or videos) from a specific collection by collection ID, with optional filters for type, sort order, page, and results per page.
Resources
The server provides the following URI-addressable resources:
pexels-photo://{id}: Access a specific photo by IDpexels-video://{id}: Access a specific video by IDpexels-collection://{id}: Access a specific collection by ID
Error Handling
The server attempts to provide informative error messages for common issues like invalid API keys, rate limits, or missing resources. Successful responses also include the current Pexels API rate limit status (remaining requests, reset time) in the output.
Attribution Requirements
When using the Pexels API, you must follow their attribution requirements:
- Always show a prominent link to Pexels (e.g., "Photos provided by Pexels")
- Always credit photographers (e.g., "Photo by John Doe on Pexels")
License
ISC
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。