Skip to Content

Connect OpenAlex MCP to Your AI Agent

Find papers and verify references with your OpenAlex account.

20,000 free app calls every month(paid services billed separately)

Try a OpenAlex MCP Task

Copy a prompt into your agent with the oo Skill installed. Add your page links and source notes before running it.

oo SkillOpenAlex MCP

Search scholarly research and manage your author profile

Find papers and verify references with your OpenAlex account.

/oo OpenAlex MCP: Find recent papers about [topic] and return their titles, publication years, DOIs and links. Preserve the query so I can reproduce the search.

Start Working with OpenAlex MCP

  1. Install OOMOL

    Set up oo CLI and the oo Skill in your agent.

    Install OOMOL →
  2. Connect OpenAlex MCP

    Sign in with your OpenAlex account.

    Connect OpenAlex MCP→
  3. Give Your Agent a Task

    Use /oo with the pages to read, the changes to make, and where to save the result.

    Connection Guide →
  • An OpenAlex account.
  • Queries use your OpenAlex account budget.
  • Author profile changes and alert management require your explicit instruction.

OpenAlex MCP Tools

Find papers and verify references with your OpenAlex account.

Search scholarly research and manage your author profile

Find papers and verify references with your OpenAlex account.

23 tools

Search Works

Search OpenAlex for scholarly works (papers, preprints, books, datasets). mode="keyword" (default) supports Boolean syntax: AND, OR, NOT, "quoted phrases", parentheses. By default it searches titles, abstracts and keywords: a phrase in the query that names an OpenAlex keyword also matches works carrying that keyword (search_in to change). Relevance-sorted results are reranked by default: the top 100 are reordered by how well each work answers the query, so the first results are the most on-topic ones and rerank_score says how sure the reranker is (rerank=false to turn it off). mode="semantic" matches by meaning and is best for descriptive or long queries (up to 2,000 characters; max 50 results; no min_citations/countries filters). mode="exact" matches words without stemming. Omit query to list works by filters alone (e.g. everything by an author, institution or funder). For anything the structured parameters can't express (nested Boolean groups across fields, exclusions, proximity, exact phrases, wildcards) pass an OQL query in `oql` instead; the OQL reference is in the server instructions and at https://help.openalex.org/access/oql/. Set preview=true to get only the result count, the canonical OQL and a small sample, which is the cheap way to tune a query before running it. Every response includes the canonical OQL and a reproduce_url. Returns compact records: title, year, authors (first 5), venue, citations, FWCI, open-access link, primary topic, truncated abstract. Use get_work for a full record.

openalex_mcp.search_works

Get Work

Fetch the full record for one scholarly work by OpenAlex ID (W2741809807), DOI (10.7717/peerj.4375 or a doi.org URL), PMID, or PMCID. Returns the authors with affiliations and ORCIDs (all of them up to 100; a bigger collaboration lists the first 100, the last and the corresponding authors, numbered, with authors_total), the full abstract, venue, open-access links, topics, keywords, funding, citations in every year the API counts, and related works.

openalex_mcp.get_work

Resolve References

Check up to 25 references against OpenAlex in one call and report what each one matched. Each item may be a DOI, PMID, OpenAlex ID, or a free-text citation (e.g. "Piwowar et al. (2018) The state of OA. PeerJ"). IDs are looked up exactly; free-text citations are matched on title with a confidence rating (exact, likely, uncertain, none). Use it to verify a bibliography, detect fabricated or garbled citations, fill in missing DOIs, or turn a reading list into OpenAlex IDs.

openalex_mcp.resolve_references

List Citations

List works connected to a given work: direction="citing" (default) returns works that cite it; "references" returns the works it cites; "related" returns OpenAlex's related works (similar topic and citation neighbourhood). Useful for tracing influence, finding follow-up studies, or reading a paper's bibliography. Supports the same year/type/open-access filters as search_works.

openalex_mcp.list_citations

Search Entities

Find OpenAlex entities by name and/or filters, returning IDs plus a short profile. Entity types: authors (researchers), institutions (universities, labs, companies), sources (journals, conferences, repositories), topics (research areas), funders, publishers. Use it to resolve a name to an ID before filtering works, or as a directory. It is the right tool for expert finding: authors currently at an institution working on a topic (institution_ids + topic_ids, sort by works_count or h_index; each result reports works_in_topic), journals in a field that are open access (sources + topic_ids + is_oa), institutions of a type in a country. Author results include current institutions, h-index and top topics so the right person can be picked when names collide.

openalex_mcp.search_entities

Get Entity

Fetch the full profile of one non-work entity by OpenAlex ID, or by ORCID (authors), ROR (institutions), or ISSN (sources). Includes works and citation counts, h-index, works/citations by year, top topics, affiliation history (authors), and identifiers.

openalex_mcp.get_entity

Group Works

Aggregate works matching a query and/or filters, counting them by one dimension: author, institution, institution_type, country, source (journal), publisher, funder, year, type, topic, subfield, field, domain, keyword, oa_status, is_oa, top_10_percent, top_1_percent, language, or sdg. Answers "who are the top authors on X", "which institutions publish most on Y", "how has research on Z grown per year", "which journals carry the most papers on W", "who does institution A collaborate with" (institution_ids + group_by institution). Returns each group's ID, display name and work count, sorted by count. Keyword/exact queries aggregate over all matching works; semantic queries aggregate over the 50 most relevant works only. For two or three dimensions in one call (by year and country, by field and open access status) or numbers beyond the count (mean FWCI, percent open access, share), use calculate_works instead of one group_works call per value. Accepts an OQL query in `oql` for complex selections (the group by is added from group_by if the query has none). Note: group_by author over institution-filtered works also counts co-authors from other institutions; for "researchers AT institution X on topic Y" use search_entities with institution_ids and topic_ids instead.

openalex_mcp.group_works

Analyze Works

Build a one-call profile of any set of works defined by a query and/or filters: an institution's output, a funder's portfolio, an author's career, a topic, a country, a journal. Returns total works, open-access share by status, share of works in the top 10% and top 1% most-cited (field-normalized), counts by year and by type, and the top fields, topics, institutions, countries, sources, funders and authors, plus international and industry collaboration shares. Use it for research-office, library, and funder reporting questions ("summarize our 2024 research", "how much of NIH-funded work at UW is open access", "who does MIT collaborate with on AI"). Pick sections to keep the response small. Keyword queries only (no semantic mode). Each section costs one cheap API call.

openalex_mcp.analyze_works

Read Docs

Return a canonical OpenAlex documentation page, bundled from help.openalex.org: oql (OQL: the OpenAlex Query Language (overview)); oql_spec (OQL specification (normative, every rule and error code)); api_quick_reference (OpenAlex API quick reference for agents (entities, filters, syntax)); fixing_authors (Fixing author profiles: claiming, adding and removing works, merging duplicates); author_curation (Author curation API: the exact curation payloads and how they are applied). Use oql_spec when an OQL query is rejected and the fix-it isn't enough, api_quick_reference for entity fields and filter names, and fixing_authors before curating a profile.

openalex_mcp.read_docs

Find Experts

Find the researchers who work most on a topic, optionally at an institution or in a country, ranked with evidence: how many matching works, how many in the last few years, h-index, current institution, topic share, and up to five matching titles each. Use it for expert finding, reviewer and panel search (exclude_coauthors_of + exclude_institution_ids for conflicts), collaborator search (institution_ids), and "who at my university works on X" (institution_ids with institution_scope="current"). Describe the topic as a Boolean keyword query (AND, OR, NOT, "quoted phrases", wildcards*): the census then covers every matching work in OpenAlex. Turn a descriptive paragraph into synonyms grouped with OR and concepts joined with AND rather than using semantic mode, which sees only the 50 most relevant works. Topic IDs (topic_ids) are coarse; text is usually better. Pass an OQL selection in `oql` for full control. One call replaces the search_entities / group_works / get_entity chain and costs three to five API requests.

openalex_mcp.find_experts

Find Keywords

Find the OpenAlex keywords for a topic, the first step of a thorough (high-recall) search. OpenAlex tags works with keywords (e.g. microplastics, human-health, antimicrobial-resistance) that also catch works using other wordings, other languages, or no abstract at all. search_works and keyword_search already match the keywords that the search's own phrases name; use this to find keywords that mean a facet under other names. Give the topic as a sentence (description) and, for better coverage, each facet's main phrase and synonyms (phrases). Returns candidate keywords with a match score, how many works carry each, and their three most-cited titles, so you can keep the ones that mean each facet and drop the rest. Then pass them to keyword_search. Costs about $0.01 (one /text/keywords call) plus a few cheap lookups.

openalex_mcp.find_keywords

Keyword Search

Build and measure a thorough search: each facet matches on its text (over titles, abstracts and the keywords the text names) OR on the keywords you chose for it, and all facets must match. Returns the combined OQL with a reproduce_url, and counts for every part: the search alone (what search_works finds for the facets' text), what the chosen keywords add, the combined total, and each facet's text, keyword and keyword-only counts, plus random samples of the whole search and of the works found only through keywords, so you can check precision. Filters (open access, years, types, language, any OQL condition) apply to every count. Use after find_keywords; then list the results with search_works(oql=<combined oql>). Every facet should have text; give a facet keyword_ids only when a keyword really means it.

openalex_mcp.keyword_search

Calculate Works

Run an OQL calculation and get the calculated groups: split a set of works by one to three fields, named values, searches, conditions or bins, and calculate count, mean/median/sum/min/max of a number, percent of a yes/no field, or each group's share. Write it as a pipeline: get works where <conditions>; then, group those works by <field>; finally, summarize using <measures>. For one row per author, institution, source, publisher, funder, country or topic, start with them and say which works count, e.g. get authors at [University of British Columbia](I141945490) since 2022 who published works where title-abstract has kelp; then, summarize each author using count and mean FWCI (`at` reads the author's own record; `in [Asia](Q48)` for institutions; then, group each author's works by year for a further split). Or compare named things in one step, e.g. get works where topic is [CRISPR and Genetic Engineering](T10878); then, compare institution [Massachusetts Institute of Technology](I63966007) versus [Stanford University](I97018004) versus [Harvard University](I136199984) using count, mean FWCI, and percent open access. The full guide is the OQL reference in the server instructions (read_docs topic oql). Check a new query with check_oql first (free: limits with fixes, time estimate, price). Returns one row per group, keyed by the OQL words of each calculation (count, mean FWCI, ...), nested splits under groups, the summary (summary.all for the whole starting set; with two or more splits, summary.splits with each split's groups on their own, computed from the works: read these, never sum or average group rows), groups_count and next_page, the price, the canonical OQL and a reproduce_url. A query with no split or calculation gets then, summarize using count; a query that starts from authors, institutions, sources, topics, funders or publishers with no split lists them with their own fields. Retracted works are left out unless include_retracted=true or the query says otherwise.

openalex_mcp.calculate_works

Check Oql

Free check of any OQL query before running it, the calculation pipelines above all: whether it is valid, every problem with its fix (a parse error, a fourth split, too many groups, too slow), the time estimate against the ~10-second budget, the price in credits and USD, and the canonical text with each entity's name in brackets so you can confirm the IDs mean what you think. The query is checked as calculate_works would run it (retracted works left out unless include_retracted=true). When it is not valid, apply the fix and check again.

openalex_mcp.check_oql

List My Alerts

The user's email alerts: each saved search that emails new matching works, with its frequency, when it last sent and when it next checks. Set include_saved_searches to also list saved searches with no alert. Use it to answer "what alerts do I have?" or to find an id to change or delete.

openalex_mcp.list_my_alerts

Create Alert

Email the user new works that match a search, daily, weekly or monthly (saved as a saved search with an alert, visible on openalex.org under My alerts). Build the search with search_works first and pass its OQL (or an api.openalex.org works URL). The first email covers works added from now on, and an email goes out only when there are new works. Returns the alert and the newest works the search matches today: show the user a few so they know what will arrive. Refusals come back with a code: works_collection_cannot_alert, collection_type_mismatch (the message names the right field), semantic_search_cannot_alert, search_is_empty, alert_requires_works_search, collection_not_found, saved_search_exists (the user already saved this search, maybe without an alert: turn it on with update_alert on the existing id).

openalex_mcp.create_alert

Update Alert

Change one of the user's alerts: how often it emails (daily, weekly, monthly), or "off" to stop the emails but keep the saved search; or rename it. Turning an alert back on for a saved search also uses this. Ids come from list_my_alerts.

openalex_mcp.update_alert

Delete Alert

Delete one of the user's alerts together with its saved search. To stop the emails but keep the saved search, use update_alert with frequency "off" instead. Confirm with the user first.

openalex_mcp.delete_alert

Get My Account

Who is connected: name, email addresses (and which are verified), which API key this connection spends (personal or organization), the author profile this account has claimed (with a compact summary: names, institutions, topics, works count), the claim's status, and claim_eligibility: "instant" means a claim from this account is approved immediately (a verified academic, institutional or government email), "review" means the claim needs ORCID sign-in or a link to one of the user's papers on the profile that lists the account email (checked automatically within minutes; a web page alone never passes). Call this first for anything about the user's own profile.

openalex_mcp.get_my_account

Claim Author Profile

Claim an OpenAlex author profile for the connected account so it can be curated (one per account). Confirm the profile with the user first (show its name, institutions, works count and a few titles from search_works). Approved instantly if any verified email on the account is from a university, research institute or government agency (get_my_account reports claim_eligibility). Otherwise, first suggest the user add their university email in Settings at openalex.org (they keep their current email); that makes the claim instant. If the profile has their ORCID iD, they can sign in with ORCID on the profile page instead. If neither works, ask for a link (or DOI) to one of their papers ON THIS PROFILE that lists their OpenAlex account email. A web page alone never passes, not even their page on a university's website, and neither does a page with only their name. The claim is checked automatically within minutes; if it fails, the result says what is missing and the user can send a new link by calling this again.

openalex_mcp.claim_author_profile

Find Candidate Works

Works that are probably this author's but are not on their profile, from up to three sources: (1) name: the website's name ladder over raw bylines (as typed, reversed, initials, then looser word order) with a surname-plus-given-name gate, ranked by how much of the name the byline matches; (2) orcid: works carrying the ORCID in OpenAlex plus works listed on the public ORCID record (readable without login unless the author made them private); (3) siblings: other author profiles with the same name, with overlap signals, which may be duplicates of this person. Every work reports this_authorship (the byline that would be attached, with affiliations and coauthors) so the user can be asked about anything unclear. Pass alternate names (from get_my_account, the profile, or a CV) one call at a time; for common names add institution, topic or year filters.

openalex_mcp.find_candidate_works

Submit Curations

Submit corrections to the user's claimed author profile as OpenAlex curations, up to 100 per call: add_work (attach a byline on a work to the profile), remove_work (detach the profile from a work), set_display_name, set_full_name (the name used to match future works), set_orcid, remove_orcid, and cancel (withdraw a pending curation). Every correction is reversible by the opposite action and each item succeeds or fails on its own. Only submit what the user has agreed to: propose removes and adds with the evidence first, ask about anything that does not clearly fit. Adds are capped at 1,000 per rolling 24 hours. Curations apply on the nightly data refresh and are live within about two days; track them with list_my_curations. Do not re-check in minutes and conclude they failed.

openalex_mcp.submit_curations

List My Curations

The corrections this account has submitted and their status: pending (waiting for the nightly refresh), applied (live), superseded (a newer correction to the same item, by this user or someone else, superseded it, so it will never apply; superseded_by names that correction), or timed_out (not seen live after a week; rechecked daily). Each row carries a plain-language description. Use it to report progress or to find a curation_id to cancel.

openalex_mcp.list_my_curations