Primo MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| primo_searchA | Search the university library catalogue and subscribed databases. Args: query: Search terms (e.g. "machine learning entrepreneurship"). field: Search field -- "any" (default), "title", "creator", "sub" (subject), "isbn", "oclcnum". scope: "everything" for local catalogue + subscribed databases, "catalogue" for local only. sort_by: "rank" (relevance, default), "date" (newest first), "title" (alphabetical). limit: Number of results to return (1-50, default 10). offset: Pagination offset (default 0). Use to get the next page of results. resource_type: Filter by type -- "books", "articles", "journals", "dissertations", "conference_proceedings". date_from: Start year filter (YYYY format, e.g. "2020"). date_to: End year filter (YYYY format, e.g. "2025"). peer_reviewed: Set to true to show only peer-reviewed items. Returns: Formatted search results with title, authors, year, identifiers, and availability. |
| primo_get_recordA | Get full details for a single library record. Use the record ID from primo_search results to fetch complete metadata including abstract, all authors, subjects, identifiers, and availability. Args: record_id: The Primo record ID (from search results, e.g. "alma991234567890" or "cdi_crossref_primary_10_1234"). Returns: Full record details including title, authors, abstract, identifiers, and availability. |
| primo_suggestA | Get autocomplete suggestions for a search term. Useful for refining searches, checking subject headings, or exploring related terms before running a full search. Args: query: Partial search term (e.g. "entrepre" or "machine lear"). Returns: List of suggested search terms. |
| primo_citeA | Generate formatted citations for library records. Args: record_ids: List of Primo record IDs to cite. style: Citation style -- "apa7" (default), "harvard", "chicago", "ieee", "vancouver". Returns: Formatted citations. Note: always verify generated citations before submission. |
| primo_exportA | Export library records to reference manager formats. Args: record_ids: List of Primo record IDs to export. format: Export format -- "bibtex" (default), "ris", "csv". Returns: Formatted export data ready for import into reference managers (Zotero, Mendeley, EndNote). |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
Each tool has a distinct purpose: search, get details, cite, export, and suggest. No overlapping functionality.
All tool names follow a consistent 'primo_verb' pattern, making them predictable and easy to distinguish.
5 tools cover the core library catalog operations without being excessive or insufficient.
The set covers search, retrieval, citation, export, and suggestion, which are the key interactions for a library catalog.