Claude Desktop
桌面端 · 免费增值 · Proprietary
Anthropic 官方推出的 Claude AI 桌面应用程序。支持 MCP 服务器以扩展功能。
WindowsMacOS
MCP
jina-ai/MCP
Jina AI提供的远程MCP服务器，通过Reader、Embeddings和Reranker API提供网页内容提取、网页搜索、学术搜索、图像搜索、查询扩展、文档重排及去重等功能。
安装
npx mcp-remote https://mcp.jina.ai/v1 --header "Authorization: Bearer ${JINA_API_KEY}"客户端配置
{
"mcpServers": {
"jina-mcp-server": {
"command": "npx",
"args": [
"mcp-remote",
"https://mcp.jina.ai/v1",
"--header",
"Authorization: Bearer ${JINA_API_KEY}"
]
}
}
}工具（28）
primer
Get current contextual information for localized, time-aware responses
read_url
Read a web page or PDF as markdown.
capture_screenshot_url
Capture a screenshot of a web page via Reader API
guess_datetime_url
Guess a page's publish or last-update datetime, with a confidence score
search_web
Search the web.
search_arxiv
Search academic papers and preprints on arXiv repository via Reader API
search_ssrn
Search academic papers on SSRN (Social Science Research Network) via Reader API
search_images
Search the web for images via Reader API
search_jina_blog
Search Jina AI news and blog posts at jina.ai/news
sort_by_relevance
Rerank documents by relevance to a query via Reranker API
deduplicate_strings
Get top-k semantically unique strings via Embeddings API and submodular optimization
extract_pdf
Extract figures, tables, and equations from PDF documents (arXiv papers or any PDF URL) using layout detection
exclude_tools
Comma-separated tool names to exclude
include_tools
Comma-separated tool names to include
exclude_tags
Comma-separated tags to exclude
include_tags
Comma-separated tags to include
max_tokens
Cap read_url response size in tokens.
search
search_web, search_arxiv, search_ssrn, search_images, search_jina_blog
read
read_url, capture_screenshot_url
utility
primer, guess_datetime_url, extract_pdf
rerank
sort_by_relevance, deduplicate_strings
search_web_deep
search_web, then read_url with question on the pages you pick
parallel_search_web
pass an array to query / url on the singletons
expand_query
rewrite the query yourself; the endpoint returned one near-copy of the input
classify_text
classify with the model; label scores differed by ~0.006, which is noise
deduplicate_images
the response carried base64 JPEG data, not just the selected items
search_bibtex
read the citation from the publisher or DBLP page directly; both backends were failing live
show_api_key
nothing.
本页信息摘自该项目的 README。 查看 README
支持的客户端
该服务器 README 中提到的客户端：
相关 MCP 服务器
Firecrawl MCP Server
mendableai/firecrawl-mcp-server
Firecrawl MCP Server是一个集成Firecrawl网页抓取能力的模型上下文协议服务器，提供丰富的网页抓取、搜索和内容提取功能。
Exa Web Search
exa-labs/exa-mcp-server
Exa MCP Server是一个为AI助手（如Claude）提供网络搜索功能的服务器，通过Exa AI搜索API实现实时、安全的网络信息获取。
ArXiv
blazickjp/arxiv-mcp-server
ArXiv MCP Server是一个连接AI助手与arXiv研究库的桥梁，通过MCP协议实现论文搜索和内容访问功能。
sail
lakehq/sail
Sail是一个旨在统一流处理、批处理和计算密集型（AI）工作负载的项目，提供了Spark SQL和Spark DataFrame API的替代方案，支持单机和分布式环境。
OpenAPI Proxy
janwilmake/openapi-mcp-server
一个为Claude/Cursor设计的OpenAPI规范探索服务器，通过三步流程帮助用户搜索和理解API文档。
Excel MCP Server
haris-musa/excel-mcp-server
一个无需安装Excel即可操作Excel文件的MCP服务，支持创建工作簿、读写数据、格式设置、图表生成等功能。