Northwestern University Libraries Digital Collections API
Server Details
Agent integration with the Northwestern University Libraries Digital Collections API
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- nulib/dc-api-v2
- GitHub Stars
- 15
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 8 tools
Most tools have clear boundaries: search and similarity-search are distinct query modes, and view-* tools are explicitly for interactive viewing while get-work and list-collections return metadata. However, get-work vs view-work and list-collections vs view-collection could cause mild confusion, and view-search-results refers to a 'search-works' tool that is actually named 'search'.
Tool names mostly follow a lowercase hyphenated verb-object pattern like get-work, list-collections, and view-work. However, 'search' lacks an object, 'similarity-search' is formatted as a compound noun rather than a verb phrase, and the description for view-search-results references a non-existent 'search-works' tool name.
Eight tools is a well-scoped set for a digital collections API. Each tool serves a distinct function covering search, retrieval, similarity, and interactive viewing without feeling bloated or sparse.
The tool surface covers the core read-only workflows: searching, similarity matching, retrieving work metadata, listing collections, and viewing results interactively. A minor gap is the lack of a direct get-collection metadata tool separate from list-collections, but agents can likely work around this.
Available Tools
8 toolsget-workGet WorkBRead-onlyIdempotentInspect
Retrieve the full metadata for a work from the NUL Digital Collections.
Inputs: work_id (required).
list-collectionsList CollectionsBRead-onlyIdempotentInspect
List collection records from the NUL Digital Collections.
Inputs: page, max_results, public_only. Returns: data, info, explain, pagination, +1 more
searchSearchARead-onlyIdempotentInspect
Search for works in the Digital Collections using field-based and/or natural language queries. If both a natural language query and specific field values are provided, the natural language query will take priority, using the specified field values as additional constraints. The result will also include a list of aggregations that show how many results match different values for certain fields. For example, you could see how many results match each collection, work type, or visibility and use that information to refine your search. Perform an empty search to retrieve all works and their aggregations. NOTE: Structured field values enclosed in double quotes will be treated as exact, case-sensitive matches, while unquoted values will be treated as full-text searches.
Inputs: page, query, fields, max_results, +1 more. Returns: data, info, explain, pagination, +1 more
similarity-searchSearch for Similar WorksARead-onlyIdempotentInspect
Find works that are similar to a given work. Uses semantic similarity based on work embeddings.
Inputs: work_id (required), page, max_results, public_only. Returns: data, info, explain, pagination, +1 more
view-collectionView CollectionBRead-onlyIdempotentInspect
View a collection from the NUL Digital Collections in an interactive viewer.
Inputs: collection_id (required). Returns: iiifContentUrl
view-search-resultsView Search ResultsCRead-onlyIdempotentInspect
View results from the search-works tool in an interactive viewer.
Inputs: page, query, fields, max_results, +1 more. Returns: iiifContentUrl
view-similar-worksView Similar WorksARead-onlyIdempotentInspect
View results from the similarity-search tool in an interactive viewer.
Inputs: work_id (required), page, max_results, public_only. Returns: iiifContentUrl
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
arXiv and OpenAlex/Crossref paper search (an open Google Scholar alternative) as agent tools.
Agent verification tools: CSV quality, citation checks, AI-readiness audits, requirement extraction
W3C DID issuance and verification for autonomous AI agents
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables agents to find, read, and cite digitized primary sources published via IIIF — searching several institutions' catalogues, resolving item pages to manifests, pulling page images or regions for vision models, and generating citations with rights and provenance. Runs read-only over stateless Streamable HTTP with no login.AGPL 3.0
- AlicenseNot gradedqualityCmaintenanceEnables agents to render document pages as images, record validated structured entries with page evidence and optional figures, and search collections by meaning through MCP tools.MIT
- FlicenseNot gradedqualityCmaintenanceIntegration Infrastructure Agents Actually Control39-
- AlicenseAqualityBmaintenanceEnables AI models to search and retrieve bibliographic and digitized records from Swiss academic libraries (swisscovery, e-rara, e-periodica, e-manuscripta) via open protocols without requiring API keys.161MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.