Aryn Local MCP Server
Enables processing PDFs via Aryn's API, typically used with a filesystem MCP server for file management.
README
Aryn Local MCP Server
Installation
Prerequisites
- Python 3.12 or higher. Install it here
- uv - Fast Python package installer and resolver
- An Aryn API key. You can create an account and receive a key for free here
- This MCP server works best in combination with a file system MCP server (see installation instructions below)
- An MCP server client like Claude Desktop (Recommended) or Claude Code
Filesystem MCP
The Aryn MCP server requires absolute file paths to pdfs you want processed as inputs, so it works best when paired with an MCP server that can automatically manage files on your computer. Here is how to install one for Claude Desktop:

More documentation for the filesystem MCP server can be found here.
One-Click Install for Claude Desktop (Claude Desktop only)
Instead of manually installing this MCP server, Claude Desktop allows for an easy one-click extension:
Download the extension: Retrieve the provided .dxt file from this repository, or download it for macos here and linux here.
Find the .dxt extension: Navigate to the folder where the file was downloaded and double click to install. Follow the installation steps when prompted

Restart Claude Desktop
Now you're ready to go!
For more details, refer to the Claude Desktop Extensions documentation.
Manual Installation
If you're manually installing this MCP server, you need to install uv first, which provides the uvx command. Install it here.
After installation, you'll have access to both uv and uvx commands. The uvx command is what you'll use to run this MCP server.
Next, add the following configuration to your MCP client config file
{
"mcpServers": {
"Aryn Local MCP Server": {
"command": "uvx",
"args": [
"aryn-mcp-server"
],
"env": {
"ARYN_API_KEY": "YOUR_ARYN_API_KEY",
"ARYN_MCP_OUTPUT_DIR": "<full path to directory where files will get saved (ie Users/username/Downloads)>"
}
}
}
}
For client specific config implementation, see below:
Troubleshooting
If you encounter spawn uvx ENOENT errors:
-
Verify uv installation: Run
which uvxin your terminal to find the correct path -
Use the full path to uv: Replace
"command": "uvx"with"command": "<full path to uvx>"
If you encounter file permissions errors, ensure that the path is expanded out and passed, MCP client tend to treat them as literal directory names. For specific issues:
-
Input Directory: Ensure that the filesystem connector has access to the directory, and it is read accessible.
-
Output Directory: Ensure that the directory is write accessible.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.