About MCP for VuFind
MCP for VuFind connects VuFind's Swagger API to an LLM for literature search. Based on fastmcp, it currently supports DAIA and the VuFind Swagger API.
Key features
- 01Connects to VuFind Swagger API
- 02Supports DAIA
- 03Searches literature
Use cases
- 01Search literature through an LLM
- 02Connect to a locally accessible VuFind API
MCP support
It is an MCP server that exposes VuFind search capabilities to LLM clients. API endpoints are configured in config.ini, and calls originate from the local machine.
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 READMEMCP for VuFind
Scope
This is a simple MCP server based on https://github.com/jlowin/fastmcp the goal is to enable the integration of VuFinds Swagger API into an LLM like Sonet. This enables the LLM to use Vufind and search for literature
Supported Systems
Currently this MCP server supports DAIA and VuFinds Swagger API
Installation
just use pip install -r requierments.txt
configure your APIs
Claude executes the MCP server on your local machine each API call originates from your system . This implies that the API has to be accessible from your local machine. Define your API endpoints in config.ini
Configure Claude
To set up Claude Desktop as a Ghidra MCP client, go to Claude -> Settings -> Developer -> Edit Config -> claude_desktop_config.json and add the following:
{
"mcpServers": {
"Vufind": {
"command": "python",
"args": [
"C:/ubmcp/UBBSMCP/server.py ",
"C:/ubmcp/UBBSMCP/config.ini"
]
}
}
}
adjust the paths to your server.py and config.ini acordingly
claude in action
A small hammer indicates that claude uses an MCP server. A click on the hammer icon shows to exported MCP functions.
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.