PDF Search for Zed

Name: PDF Search for Zed
Author: freespirit

@freespirit

代码仓库

关于 PDF Search for Zed

An MCP server extension for Zed that retrieves relevant pieces from a PDF file

基本信息

分类

文件与存储

运行时

python

传输方式

stdio

发布者

freespirit

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "pdfsearch-zed": {
      "command": "uv",
      "args": [
        "venv"
      ]
    }
  }
}

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 Search for Zed?

PDF Search for Zed is a document search extension for the Zed editor that enables semantic search through PDF documents. It integrates with Zed’s AI Assistant, allowing users to query PDF content and add relevant sections directly to the assistant’s context. The extension is built on a Python-based MCP (Model Context Protocol) server and currently requires an OpenAI API key for generating embeddings and uv for managing the Python environment.

How to use PDF Search for Zed?

Clone the repository, set up the Python virtual environment with uv venv and uv sync, then build the search database by running uv run src/pdf_rag/rag.py build "file1.pdf" "dir1" .... Configure Zed’s context_servers in its settings to point to the extension path. In Zed’s AI Assistant panel, type /pdfsearch <query> to search and add results to the assistant’s context.

Key features of PDF Search for Zed

Semantic search across PDF documents
Integrates results directly into Zed’s AI Assistant
Support for multiple PDFs and directories
Optional support for additional file formats beyond PDF
Self-contained vector store (already implemented)
Manual index building before first use

Use cases of PDF Search for Zed

Querying a collection of PDF research papers from within Zed’s AI Assistant
Searching through software manuals or technical documentation embedded in PDFs
Building a searchable knowledge base from local PDF files for coding assistance
Extracting relevant sections from legal or compliance documents during editing

FAQ from PDF Search for Zed

What are the prerequisites for using PDF Search for Zed?

You need an OpenAI API key to generate embeddings and uv installed on your system. The extension also requires cloning the repository and manually building the search index.

How do I build the search index?

Run uv run src/pdf_rag/rag.py build with one or more PDF files or directories as arguments. Indexing may take a few minutes depending on document size.

Can I search multiple PDFs at once?

Yes. You can provide multiple file paths and directories as arguments when building the index. The extension will search across all indexed documents.

Does PDF Search for Zed work offline?

No, it currently requires an internet connection and an OpenAI API key because embeddings are generated via OpenAI’s API. Future versions plan to support self-contained embeddings.