MCP Research Server
About
# MCP Research Server A FastMCP server for searching and extracting research papers from arXiv. ## Local Development This project uses `uv` for dependency management: ```bash uv run research_server.py ``` ## Deployment on Render.io Render.io doesn't support `uv` natively, so this project includes: -…
Explore
- Built on the FastMCP framework.
- Searches and extracts papers from arXiv.
- Deployable on Render.io.
- Specifies Python 3.11.11 runtime.
- Includes Render deployment configuration.
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
MCP Research ServerCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Render.io doesn't support uv natively, so this project includes:
- requirements.txt: Generated from pyproject.toml using uv pip compile
- render.yaml: Render deployment configuration
- runtime.txt: Specifies Python version for Render
To deploy:
1. Push your code to GitHub
2. Create a new Web Service on Render
3. Connect your GitHub repository
4. The service will automatically:
- Use Python 3.11.11
- Install dependencies from requirements.txt
- Start the server on port provided by Render
When you update pyproject.toml dependencies, remember to regenerate requirements.txt:
uv pip compile pyproject.toml --no-emit-find-links > requirements.txt
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"mcp research server": {
"mcp-research-server": {
"command": "uv",
"args": [
"run",
"research_server.py"
]
}
}
}
}McpServers
{
"mcp-research-server": {
"command": "uv",
"args": [
"run",
"research_server.py"
]
}
}A FastMCP server for searching and extracting research papers from arXiv.
Local Development
This project uses uv for dependency management:
uv run research_server.py
Deployment on Render.io
Render.io doesn't support uv natively, so this project includes:
- requirements.txt: Generated from pyproject.toml using uv pip compile
- render.yaml: Render deployment configuration
- runtime.txt: Specifies Python version for Render
To deploy:
1. Push your code to GitHub
2. Create a new Web Service on Render
3. Connect your GitHub repository
4. The service will automatically:
- Use Python 3.11.11
- Install dependencies from requirements.txt
- Start the server on port provided by Render
When you update pyproject.toml dependencies, remember to regenerate requirements.txt:
uv pip compile pyproject.toml --no-emit-find-links > requirements.txt
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
