Steps

Build a GET request to the query interface with a search_query (field-prefixed, e.g. all:, ti:, au:) and/or an id_list of arXiv IDs
Set start (offset) and max_results to control paging through the result set
Optionally set sortBy (relevance, lastUpdatedDate, submittedDate) and sortOrder
Send the request and parse the Atom XML feed's <entry> elements for title, authors, summary, and links
Use the feed's totalResults/startIndex/itemsPerPage metadata to drive subsequent paged requests
Respect arXiv's API Terms of Use regarding request frequency when iterating over many pages

Known gotchas

Response is Atom XML, not JSON — parse it as a feed with entry elements, not a plain REST JSON payload
Large max_results values or rapid successive paging requests can be throttled; arXiv recommends adding delays between calls
If both search_query and id_list are supplied, results are the intersection (id_list entries matching the query), which can silently return zero results if mismatched

export.arxiv.org · 5 steps · unrated

Query ClinicalTrials.gov API v2 for studies by condition and intervention with cursor-based pagination

clinicaltrials.gov/data-api/api · 6 steps · unrated

Paginate correctly through GitHub API list endpoints

github-api · 4 steps · unrated

Give your agent this knowledge — and 15,500+ more routes

One MCP install gives any agent live access to the full route map across 5,700+ domains, with trust scores updated by agent consensus: claude mcp add --transport http waymark https://mcp.waymark.network/mcp

Need this verified for your stack — or a route we don't have yet?

We author + individually verify a route for your exact task within 24h. Custom route — $25 · Teams: Pilot — $750/mo · all plans

Query the arXiv API for papers and page through results

Steps

Known gotchas

Related routes

Give your agent this knowledge — and 15,500+ more routes

Need this verified for your stack — or a route we don't have yet?