- Home
- MCP servers
- MCP Scholarly Server
MCP Scholarly Server
- python
172
GitHub Stars
python
Language
6 months ago
First Indexed
2 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
Installation
Add the following to your MCP client configuration file.
Configuration
View docs{
"mcpServers": {
"adityak74-mcp-scholarly": {
"command": "uv",
"args": [
"--directory",
"/Users/adityakarnam/PycharmProjects/mcp-scholarly/mcp-scholarly",
"run",
"mcp-scholarly"
]
}
}
}You run an MCP Scholarly Server to search for academic articles via arXiv and related scholarly sources. This server exposes a search tool that lets you query articles by keyword and retrieve relevant results, helping you quickly locate scholarly content for research, coursework, or writing.
How to use
You connect to the MCP Scholarly Server using a compatible MCP client. Use the search tool by providing a keyword related to the topic you want to explore. The server will return a list of relevant articles from arXiv and other scholarly sources, enabling you to refine your search and gather credible references for your work.
Typical usage patterns include starting a session with your MCP client, invoking the search-arxiv tool with your chosen keyword, and reviewing the results. You can perform iterative searches by changing the keyword and re-running the search to build a focused collection of articles.
How to install
Prerequisites you should have before installing: Node.js and npm (or an environment that can run MCP servers). You may also use Docker if you prefer containerized execution.
Step 1: Install the MCP Scholarly server via Smithery for Claude Desktop automation.
npx -y @smithery/cli install mcp-scholarly --client claude
Step 2: If you want to run the server locally in development mode, you can use the following stdio configuration where the runtime command is uv with the development directory and run script.
{
"mcpServers": {
"mcp-scholarly": {
"command": "uv",
"args": [
"--directory",
"/Users/adityakarnam/PycharmProjects/mcp-scholarly/mcp-scholarly",
"run",
"mcp-scholarly"
]
}
}
}
Additional setup options
If you prefer a published (runtime) configuration without local development tooling, you can run the server via a pre-packaged runtime. The following is a complete stdio configuration example you can place in your MCP client settings.
{
"mcpServers": {
"mcp-scholarly": {
"command": "uvx",
"args": [
"mcp-scholarly"
]
}
}
}
Additional Docker option
If you prefer running this as a Docker container, use the published Docker server configuration to start the server.
{
"mcpServers": {
"mcp-scholarly": {
"command": "docker",
"args": [
"run", "--rm", "-i",
"mcp/scholarly"
]
}
}
}
Notes on deployment
You can also deploy using the Smithery workflow to automatically configure Claude Desktop for this MCP server. The command to initiate this is shown in the install step above.
Available tools
search-arxiv
Search arxiv for articles related to the given keyword. The tool takes a required string argument named keyword and returns a list of relevant scholarly articles.