PDF Search for Zed MCP Server

@freespirit

Basic information

About PDF Search for Zed MCP Server

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

PDF Search for Zed MCP Server config

Add this server to your MCP-compatible client using the configuration below.

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

PDF Search for Zed MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

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

Frequently asked questions

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.

Is the vector store self-contained?

Yes, the vector store is self-contained and has already been implemented. However, manual index building is still required before first use.

Comments

More Files & Storage MCP servers

Bulk Filesystem Operations MCP Server

strawgate

MCP Server for reading many files at the same time

drop.media

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

Filesystem MCP Server

cyanheads

A Model Context Protocol (MCP) server for platform-agnostic file capabilities, including advanced search/replace and directory tree traversal

MCP Filesystem Server

mark3labs

Go server implementing Model Context Protocol (MCP) for filesystem operations.

664

Storacha MCP Storage Server

storacha

Storacha MCP storage server - self-sovereign data for your AI applications.