Config is the same across clients — only the file and path differ.
{
"mcpServers": {
"zed-mcp-server-markitdown": {
"args": [
"-y",
"wrapper"
],
"command": "npx"
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
Python 3.14+ / Arch-based Users: If you encounter installation timeouts or onnxruntime dependency conflicts, please read the 🛠️ Python 3.14+ Quick Fix section below before installation.
Run this in your terminal to verify the server starts. Then let us know if it worked — your result helps other developers.
npx -y 'wrapper' 2>&1 | head -1 && echo "✓ Server started successfully"
After testing, let us know if it worked:
Five weighted categories — click any category to see the underlying evidence.
No known CVEs.
Checked wrapper against OSV.dev.
Click any tool to inspect its schema.
Be the first to review
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Others in writing / developer-tools
A Model Context Protocol (MCP) server and CLI that provides tools for agent use when working on iOS and macOS projects.
Workspace template + MCP server for Claude Code, Codex CLI, Cursor & Windsurf. Multi-agent knowledge engine (ag-refresh / ag-ask) that turns any codebase into a queryable AI assistant.
MCP server for accessing Figma plugin console logs and screenshots via Cloudflare Workers or local mode
MCP server for using the GitLab API
MCP Security Weekly
Get CVE alerts and security updates for Zed Mcp Server Markitdown and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
[!WARNING]
Python 3.14+ / Arch-based Users: If you encounter installation timeouts oronnxruntimedependency conflicts, please read the 🛠️ Python 3.14+ Quick Fix section below before installation.
This extension integrates MarkItDown as a Model Context Protocol (MCP) Server for for Zed's Assistant.
for upstream information, check MarkItDown-MCP
Turn any Documents into AI Context - Upload or reference any file, and this extension converts it to clean Markdown that AI can understand and work with without Multimodality.
It exposes one tool: convert_to_markdown(uri), where uri can be any http:, https:, file:, or data: URI.
| Category | Formats | AI Use Cases |
|---|---|---|
| Documents | PDF, Word (.docx), Excel (.xlsx), PowerPoint (.pptx) | Analyze reports, summarize presentations, extract data |
| Images | JPG, PNG, GIF (with OCR) | Read text from screenshots, analyze charts, describe images |
| Audio | MP3, WAV (with transcription) | Transcribe meetings, analyze speech content |
| Web | HTTP/HTTPS URLs | Summarize articles, extract key information |
| Data | CSV, JSON, XML | Process structured data, generate insights |
| Archives | ZIP files | Analyze multiple files at once |
# Clone the repo
git clone [https://github.com/G36maid/zed-mcp-server-markitdown.git](https://github.com/G36maid/zed-mcp-server-markitdown.git)
cd zed-mcp-server-markitdown
# Build the extension
cargo build --release
# Add as a dev extension in Zed:
# In Zed, go to Extensions → Install Dev Extension → Select this directory
Convert a PDF report:
Please analyze this PDF report and summarize the key findings.
Extract data from a spreadsheet:
Convert this Excel file to markdown and show me the top 5 entries.
Analyze a webpage:
Summarize the main points from this article form link in README.
Access through Zed's settings or the Assistant configuration UI:
{
"context_servers": {
"mcp-server-markitdown": {
"settings": {
"package_version": "latest"
}
}
}
}
package_version: Specify npm package version (default: "latest")# Clone the repo
git clone [https://github.com/G36maid/zed-mcp-server-markitdown.git](https://github.com/G36maid/zed-mcp-server-markitdown.git)
cd zed-mcp-server-markitdown
# Build the extension
cargo build --release
# Add as a dev extension in Zed:
# In Zed, go to Extensions → Install Dev Extension → Select this directory
If you encounter installation timeouts or dependency conflicts on Arch Linux or other systems that have updated to Python 3.14, it's recommended to configure uvx directly in Zed's settings.json. This uses an isolated Python 3.13 environment, bypassing upstream compatibility issues.
Ensure uv is installed on your system.
Open settings.json in Zed (Command Palette: type settings) and add the following configuration:
{
"context_servers": {
"markitdown": {
"command": "uvx",
"args": [
"--python",
"3.13",
"markitdown-mcp"
]
}
}
}
Since the first startup downloads Python 3.13 and related AI models (like Magika), it may exceed Zed's 60-second startup limit. Run it once