About Core_ac_uk Academic Articles
A lightweight MCP server for accessing academic works through the CORE.ac.uk API. It lets research-oriented applications search by keyword or retrieve an individual paper’s metadata.
Key features
- 01Search works by keywords
- 02Retrieve a work by identifier
Use cases
- 01Find academic papers matching a topic
- 02Fetch metadata for a known research paper
MCP support
Exposes CORE.ac.uk search and single-work retrieval functions to MCP clients. It runs locally over stdio and requires a CORE API key.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEMinimal MCP Server for Accessing CORE.ac.uk API
This project provides a lightweight Machine Communication Protocol (MCP) server that wraps key functionalities of the CORE.ac.uk API. It enables local programmatic access to academic content, allowing you to search works by keyword or download full metadata for individual research papers using a simple interface.
Ideal for integrating into applications or development environments that support MCP-based extensions.
API documentation: https://api.core.ac.uk/docs/v3
Installation
-
Clone repository:
git clone https://github.com/chkunkel/core_ac_uk_mcp cd core_ac_uk_mcp -
Install dependencies with uv:
uv syncWhen installed, run:
uv run <path_to_directory>/core_mcp_server_local.pyPlease add the path to the file, you don't need quotes or the < > brackets around your key.
Output (if successful):
INFO Starting MCP server 'CORE\xa0API\xa0Server' with transport 'stdio'With an API key installed in the environment, the MCP server is ready.
API Key Setup
You need to obtain an API Key on the website first.
Then create a .env file in the main directory with the following content:
CORE_API_KEY=<your key>
You don't need quotes or the < > brackets around your key.
Server Configuration
Run in console as python core_mcp_server.py
Add the following config to the program of your choice:
{
"mcpServers": {
"core_ac_uk_server": {
"command": "uv",
"args": [
"run",
"<SCRIPT_PATH>/core_mcp_server_local.py"
],
"env": {},
"working_directory": null,
"start_on_launch": true
}
}
}
Replace <SCRIPT_PATH> by the respective path to the script
Available Functions (so far)
search_works_by_keywordsdownload_single_work_by_identifier
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.