What dependencies are required to run this server?
The README only provides Go compilation instructions; the server is distributed as a compiled binary. It does not list runtime dependencies beyond the binary itself.
@sirix-v
基本情報
一个阅读本地pdf格式论文的mcp服务器
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"pdf-mcp-server": {
"url": "http://127.0.0.1:8080/sse"
}
}
}ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
上のボタンでサーバーのエンドポイントに接続し、ツール一覧を取得できます。
It is an MCP server that exposes PDF files stored in a user-specified local directory through MCP tools. It is built in Go and designed to be used with MCP-compatible clients such as Cursor, allowing them to list and read papers from a given folder.
Compile the source code with go build -o pdf-mcp-server main.go, then add the binary’s path to your environment variable (e.g., on macOS, update PATH in .zshrc). Start the server with pdf-mcp-server -pdfdir=your_paper_directory (e.g., -pdfdir=/Users/sirix/lunwen). In Cursor, configure the MCP server with URL http://127.0.0.1:8080/sse and set Cursor rules to call the find_pdf and read_pdf tools.
-pdfdir.find_pdf and read_pdf.http://127.0.0.1:8080/sse.The README only provides Go compilation instructions; the server is distributed as a compiled binary. It does not list runtime dependencies beyond the binary itself.
It serves over HTTP using Server-Sent Events (SSE) at `http://127.0.0.1:8080/sse`.
All PDF files must be stored in the local directory specified by the `-pdfdir` command-line flag when starting the server.
The server exposes two tools: `find_pdf` (to list papers in the directory) and `read_pdf` (to read the content of a paper). The exact signatures are not detailed in the README.
No authentication or authorization is mentioned in the README; the server appears to run locally with no security measures described.
Model Context Protocol (MCP) Server for reading from Google Drive and editing Google Sheets
MCP server to integrate AWS S3 and LLM

Upload once. Find, use and share across your AI workflows. drop.media is one media library for you and every AI agent you use: files added from Claude, ChatGPT, Cursor, the terminal or the web can be found, reused and sh
A Model Context Protocol (MCP) server for platform-agnostic file capabilities, including advanced search/replace and directory tree traversal
MCP Workspace Server: A secure Model Context Protocol server providing file, git, and GitHub tools for AI assistants within a sandboxed project directory.
コメント