Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Omeka MCP search Omeka items for 'Civil War' letters"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A FastMCP server that connects AI assistants to an Omeka S collection through the Omeka REST API.
Search Omeka items by text.
Fetch one item by numeric ID.
Return item metadata in a readable format.
Return public Omeka item page links instead of API links.
Support optional Omeka API credentials.
Related MCP server: mcp-openaire
Python 3.10 or newer
An Omeka S REST API endpoint
Create and activate a virtual environment, then install the dependencies:
python -m venv .venv
.\.venv\Scripts\Activate.ps1
pip install -r requirements.txtEdit config.ini:
[omeka]
items_url = http://<IP_Address>/omeka/api/items
site_url = http://<IP_Address>/omeka/s/terracotta/item/
api_key_identity =
api_key_credential =items_url is used to retrieve records. site_url is used to create browser-facing item links. API credentials can be left empty when the Omeka API is public.
Do not commit real API credentials to source control.
Run the MCP server with the default configuration:
python main.pyTo use a different configuration file:
python main.py path\to\config.inisearch_itemsSearch the Omeka collection.
Parameters:
query: Search text. Defaults to an empty string.
page: Page number, starting at 1. Defaults to 1.
limit: Number of results, from 1 to 100. Defaults to 10.
get_itemFetch one Omeka item by its numeric ID.
Parameters:
item_id: The Omeka item ID.
For item 131, the server returns:
http://<IP_Address>/omeka/s/terracotta/item/131The Omeka API record itself is fetched from:
http://<IP_Address>/omeka/api/items/131This server cannot be deployed
Provides metadata information to AI agents through the search API.
Search the Met collection, browse by department or update date, fetch full records and CC0 images.
Search and read the aicoolies catalog of AI and developer tools via a remote MCP knowledge graph.
Academic literature search, retrieval, and private library management on top of OpenAlex.
