Pdf Content Search Mcp
@juergenkoller-software
关于 Pdf Content Search Mcp
暂无概览
基本信息
配置
工具
未检测到工具
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
概览
What is Pdf Content Search Mcp?
Pdf Content Search Mcp is a Model Context Protocol (MCP) bridge that connects Claude, Cursor, and any MCP client to the PDF Content Search macOS app. It enables full‑text search and OCR across thousands of PDFs, returning results with page numbers, highlighted snippets, and bounding‑box coordinates.
How to use Pdf Content Search Mcp?
Install the PDF Content Search app (macOS 12+, one‑time purchase or 30‑day trial). The bridge ships inside the app bundle or can be built from source. Configure it with the PDF_CS_TOKEN and PDF_CS_PORT environment variables, then add it as an MCP server in Claude Desktop’s JSON config or via claude mcp add for Claude Code.
Key features of Pdf Content Search Mcp
- Full‑text search across thousands of PDFs in under a second
- Apple Vision OCR for scanned documents
- Page numbers, snippets, and bounding‑box coordinates in results
- Tools for search, filter, OCR, indexing, and document metadata
- Automatic session handling via
Mcp-Session-Idheader - Stdio transport with meaningful JSON‑RPC error codes
Use cases of Pdf Content Search Mcp
- Ask Claude to find every invoice from a specific sender in a given year
- Search a contracts folder for “data processing agreement” and return the matching PDF and page number
- Integrate local PDF search into Cursor’s AI workflows
- Query metadata (date, category, sender) across large document collections
FAQ from Pdf Content Search Mcp
What is the difference between this MCP server and the PDF Content Search app?
The MCP server is an open‑source stdio‑to‑HTTP bridge. The app owns the index, OCR engine, and search; the bridge routes requests between MCP clients and the app’s API.
What are the system requirements?
macOS 12 (Monterey) or later, Swift 5.9+ if building from source, and the PDF Content Search app (installed and running).
How do I get the API token for configuration?
Open PDF Content Search → Settings → API Server, copy the token, and set it as the PDF_CS_TOKEN environment variable. The app also provides a “Set up Claude Desktop” button.
Can I use Pdf Content Search Mcp with other MCP clients?
Yes. Any client that supports stdio MCP servers can use this bridge (e.g., Claude Desktop, Claude Code, Cursor).
What happens if the PDF Content Search app is not running?
The bridge returns a JSON‑RPC error with code ‑32000 (“Cannot reach PDF Content Search”), so the client surfaces a meaningful message instead of hanging.
搜索 分类下的更多 MCP 服务器
Google Search Console MCP server for SEOs
AminForouGoogle Search Console Insights with Claude AI for SEOs
mcp-omnisearch
spences10🔍 A Model Context Protocol (MCP) server providing unified access to multiple search engines (Tavily, Brave, Kagi, Exa), AI tools (Kagi FastGPT, Exa, Linkup), and content extraction services (Firecrawl, Tavily, Kagi). Includes GitHub search. All through a single interface.
perplexity-mcp MCP server
jsonallenA Model Context Protocol (MCP) server that provides web search functionality using Perplexity AI's API.
Perplexity MCP Zerver
wysh3MCP web search using perplexity without any API KEYS
DuckDuckGo Search MCP Server
nickclydeA Model Context Protocol (MCP) server that provides web search capabilities through DuckDuckGo, with additional features for content fetching and parsing.
评论