# io.github.cyanheads/pubmed-mcp-server (remote · pubmed.caseyjhand.com) Search PubMed/Europe PMC, fetch articles and full text (PMC/EPMC/Unpaywall), citations, MeSH terms. - Trust score: 70/100 (medium) - Change this week: +4 - Registry status: active - Liveness: live - Owner verified: no - Last scored: 2026-08-03 ## Components - remote · `pubmed.caseyjhand.com`: 70/100 (this document), [markdown](https://verifymcp.io/servers/cyanheads-pubmed-mcp-server/pubmed.md), [page](https://verifymcp.io/servers/cyanheads-pubmed-mcp-server/pubmed) - npm · `@cyanheads/pubmed-mcp-server`: 35/100, [markdown](https://verifymcp.io/servers/cyanheads-pubmed-mcp-server/cyanheads-pubmed-mcp-server.md), [page](https://verifymcp.io/servers/cyanheads-pubmed-mcp-server/cyanheads-pubmed-mcp-server) ## Channel facts - Endpoint: `https://pubmed.caseyjhand.com/mcp` - Transports: `streamable-http` - Auth: `none` - Version: `2.10.2` ## Trust breakdown How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog) Scored 2026-08-03. - **Endpoint Security**: 66/100 - The endpoint's TLS certificate is valid, in date, and uses a strong key. - Authorisation not fully verified: no authorisation is required to call this server, and 11 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe. - HTTPS is enforced; there's no plaintext access path. - The HSTS (Strict-Transport-Security) header is present. - DNSSEC is configured correctly; the domain's records validate against the full chain to the root. - **Transport & Reachability**: 100/100 - Verified streamable-http transport via a live MCP handshake. - **Schema Quality & AI Usability**: 75/100 - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name). - AI-judged instruction clarity (excellent). - Context-footprint check failed: tool/resource definitions use about 2895 tokens (~241/item across 12 items; 11 tools + 1 resources), over budget; trim descriptions and params. - Usage-examples check failed: none of the tools include examples. - **Stability & Change Management**: 27/100 - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses. - **Tool Coverage**: 100/100 - 100% of tools have a non-trivial description (not blank, and not just the tool's name). - 100% of tool parameters carry a description. - Structured output schemas are declared (100% of tools); any adoption earns full credit. - **Capabilities**: 100/100 - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28. ## Install ### Claude ```bash claude mcp add --transport http cyanheads-pubmed-mcp-server https://pubmed.caseyjhand.com/mcp ``` ### Codex ```toml [mcp_servers.cyanheads-pubmed-mcp-server] url = "https://pubmed.caseyjhand.com/mcp" ``` ### opencode ```json { "$schema": "https://opencode.ai/config.json", "mcp": { "cyanheads-pubmed-mcp-server": { "type": "remote", "url": "https://pubmed.caseyjhand.com/mcp", "enabled": true } } } ``` ### OpenClaw ```bash openclaw mcp add cyanheads-pubmed-mcp-server --url https://pubmed.caseyjhand.com/mcp --transport streamable-http ``` ### Hermes ```yaml mcp_servers: cyanheads-pubmed-mcp-server: url: "https://pubmed.caseyjhand.com/mcp" ``` ### Other ```json { "mcpServers": { "cyanheads-pubmed-mcp-server": { "type": "http", "url": "https://pubmed.caseyjhand.com/mcp" } } } ``` The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs. ## Changelog Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims. ### 2026-08-02 (score 70, +1) No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-07-31 (score 69, +1) - [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server ### 2026-07-30 (score 68, +1) - [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server ### 2026-07-28 (score 67, +1) No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-07-27 (score 66, +1) - [functional improvement] Stability: unverified → 0.03 ### 2026-07-26 (score 65) First indexed and scored. ## MCP tools (11) ### `pubmed_search_articles` (~394 tokens) Pubmed Search Articles Search PubMed with full query syntax, filters, and date ranges. Returns PMIDs and optional brief summaries. Supports field-specific filters (author, journal, MeSH terms), common filters (language, species, free full text), and pagination via offset for paging through large result sets. Input parameters: - `author` (string): Filter by author name (e.g. "Smith J") - `dateRange` (object): Filter by date range. The filter is applied only when both `minDate` and `maxDate` are non-empty; either one empty disables the entire date range. - `freeFullText` (boolean): Only include free full text articles - `hasAbstract` (boolean): Only include articles with abstracts - `journal` (string): Filter by journal name - `language` (string): Filter by language (e.g. "english") - `maxResults` (integer): Maximum results to return - `meshTerms` (array): Filter by MeSH terms. Multiple terms are AND'd — all must match. - `offset` (integer): Result offset for pagination (0-based). PubMed serves at most the first 9999 records of a result set, so this caps at 9998; narrow the query or add filters to reach anything beyond it. - `publicationTypes` (array): Filter by publication type (e.g. "Review", "Clinical Trial", "Meta-Analysis"). Multiple values are OR'd — any match qualifies. - `query` (string, required): PubMed search query (supports full NCBI syntax) - `sort` (string): Sort order: relevance (default), pub_date (newest first), author, or journal - `species` (string): Filter by species - `summaryCount` (integer): Fetch brief summaries for top N results (0 = PMIDs only). Above the 50 cap, pass the remaining PMIDs to pubmed_fetch_articles. Output parameters: - `appliedFilters` (object): Normalized filter values that were applied to the PubMed query - `effectiveQuery` (string): Sanitized query sent to PubMed after applying all active filters - `notice` (string): Optional guidance when the result set does not reflect what was asked for — a field tag PubMed ignored, a phrase it matched nothing for, a dateRange dropped for having one bound, no matches at all, o… - `offset` (number): Result offset used - `pmids` (array): PubMed IDs - `query` (string): Original query - `searchUrl` (string): PubMed search URL - `summaries` (array): Brief summaries (empty array when summaryCount is 0) - `totalCount` (number): Total matching articles ### `pubmed_fetch_articles` (~71 tokens) Pubmed Fetch Articles Fetch full article metadata by PubMed IDs. Returns detailed article information including abstract, authors, journal, MeSH terms. Input parameters: - `includeGrants` (boolean): Include grant information - `includeMesh` (boolean): Include MeSH terms - `pmids` (array, required): PubMed IDs to fetch Output parameters: - `articles` (array): Parsed articles - `notice` (string): Optional guidance when no articles were returned — points to discovery tools. Absent on successful fetches. - `totalReturned` (number): Number of articles returned - `unavailablePmids` (array): PMIDs that returned no article data ### `pubmed_fetch_fulltext` (~763 tokens) Pubmed Fetch Fulltext Fetch full-text articles from PubMed Central with structured sections and references. When PMC misses, transparently falls back to Europe PMC `fullTextXML` (structured JATS for records with a PMC counterpart), then to Unpaywall — publisher-hosted or institutional open-access copies as HTML-as-Markdown or PDF-as-text. Provide exactly one of `pmcids` (PMC IDs directly), `pmids` (PubMed IDs, auto-resolved), or `dois` (DOIs, auto-resolved to PMC via the ID Converter; preprints and EPMC-only OA fall through to the Europe PMC and Unpaywall layers). Input parameters: - `dois` (array): DOIs to resolve (e.g. ["10.21203/rs.3.rs-9010375/v1"]). Provide exactly one of `pmcids`, `pmids`, or `dois`. Resolved to a PMCID via the PMC ID Converter and returned as structured JATS when the arti… - `includeReferences` (boolean): Include reference list. Applies to `source=pmc` results only. - `maxCharacters` (integer): Per-article budget for body text, in characters. Counts `source=pmc` section and subsection text, or the `source=unpaywall` `content` body; titles, abstracts, identifiers, and references are never co… - `maxCharactersPerSection` (integer): Budget for a single top-level body section, in characters, counting the section text plus its subsections. Combine with `maxCharacters` to cap both one section and the article; the tighter of the two… - `maxSections` (integer): Maximum top-level body sections. Applies to `source=pmc` results only. - `overflowMode` (string): How to spend `maxCharacters` across an article that exceeds it. truncate: fill sections in document order, so early sections stay whole and sections past the budget are dropped (counted in `truncatio… - `pmcids` (array): PMC IDs to fetch (e.g. ["PMC9575052"]). Provide exactly one of `pmcids`, `pmids`, or `dois`. PMC IDs with no retrievable full text fall through to Europe PMC, then to Unpaywall on the DOI the chain r… - `pmids` (array): PubMed IDs. Provide exactly one of `pmcids`, `pmids`, or `dois`. Articles in PMC are returned as structured JATS; articles not in PMC fall through to Europe PMC (when EPMC has a `fullTextXML`), then… - `sections` (array): Filter to specific sections by title, case-insensitive (e.g. ["Introduction", "Methods", "Results", "Discussion"]). Applies to `source=pmc` results only. Output parameters: - `articles` (array): Full-text articles - `notice` (string): Optional guidance for a partial or empty body. A `sections`-filter miss names the requested terms and affected article id(s) and suggests retrying without `sections` or using broader headings. A meta… - `totalReturned` (number): Number of articles returned - `truncation` (object): Character accounting for full text the budget shortened. Present only when a budget actually removed characters — its absence means every returned article carries its full post-filter body. - `unavailable` (array): Per-identifier explanations for any requested PMIDs, PMCIDs, or DOIs with no returnable full text. `idType` discriminates which branch the id came from. ### `pubmed_format_citations` (~99 tokens) Pubmed Format Citations Get formatted citations for PubMed articles in one or more formats (apa, mla, bibtex, ris, vancouver). Pass a single format as a string or multiple as an array. Input parameters: - `format`: Citation format(s) to generate — single style as a string or multiple as an array. Allowed values: apa, mla, bibtex, ris, vancouver. - `pmids` (array, required): PubMed IDs to cite Output parameters: - `citations` (array): Citations per article - `notice` (string): Optional guidance when no citations were produced — points to discovery tools. Absent when at least one citation was produced. - `totalFormatted` (number): Number of PMIDs successfully formatted - `totalSubmitted` (number): Number of PMIDs submitted for citation formatting - `unavailablePmids` (array): Requested PMIDs that did not return article metadata ### `pubmed_find_related` (~142 tokens) Pubmed Find Related Find articles related to a source article — similar content (similar), articles citing this one (cited_by), or articles this one cites (references). Uses NCBI ELink as the primary source; falls back to Europe PMC then OpenAlex when NCBI is unavailable. Input parameters: - `maxResults` (integer): Maximum related articles - `offset` (integer): Result offset for pagination (0-based); page through results by incrementing by maxResults - `pmid` (string, required): Source PubMed ID - `relationship` (string): Relationship type: similar (content-based), cited_by (articles citing this one), references (articles this one cites) Output parameters: - `articles` (array): Related articles - `notice` (string): Guidance when results are empty, a fallback provider answered, or offset overshot. Absent on a clean NCBI result page. - `offset` (number): Result offset used - `relationship` (string): Relationship type used - `source` (string): Provider that answered this request - `sourcePmid` (string): Source PubMed ID - `totalCount` (number): Total related articles found before windowing ### `pubmed_spell_check` (~43 tokens) Pubmed Spell Check Spell-check a query and get NCBI's suggested correction. Useful for refining search queries. Input parameters: - `query` (string, required): PubMed search query to spell-check Output parameters: - `corrected` (string): Corrected query (same as original if no suggestion) - `hasSuggestion` (boolean): Whether NCBI suggested a correction - `original` (string): Original query ### `pubmed_lookup_mesh` (~144 tokens) Pubmed Lookup Mesh Search and explore the MeSH (Medical Subject Headings) controlled vocabulary. Returns descriptor records with tree numbers, scope notes, and entry terms, plus pagination via offset for paging past the maxResults cap. Input parameters: - `includeDetails` (boolean): Fetch full MeSH records (scope notes, tree numbers, entry terms) - `maxResults` (integer): Maximum results - `offset` (integer): Result offset for pagination (0-based). Pass the `nextOffset` from the previous response to get the following page; the exact-descriptor match is pinned to the first page only. - `query` (string, required): MeSH descriptor name or free-text term to look up Output parameters: - `nextOffset` (number): Offset to request for the next page. Omitted when this is the last page, so its absence is the end-of-results signal. - `notice` (string): Optional guidance when no descriptors matched or the offset overshot the result set — suggests spell-check, free-text search, or resetting the offset. Absent on successful result pages. - `offset` (number): Result offset this page was read from - `query` (string): Original search query - `results` (array): Matching MeSH records - `totalCount` (number): Total MeSH descriptors matching the query upstream, before the maxResults cap ### `pubmed_lookup_citation` (~117 tokens) Pubmed Lookup Citation Look up PubMed IDs from partial bibliographic citations. Useful when you have a reference (journal, year, volume, page, author) and need the PMID — deterministic citation matching, more reliable than free-text search for structured references. Each citation must include at least journal or year (ECitMatch primary-keys on journal+volume+page; author-only or volume-only inputs guarantee no match); more fields = better match accuracy. Input parameters: - `citations` (array, required): Citations to look up. More fields = better match accuracy. Output parameters: - `results` (array): Match results, one per input citation - `totalMatched` (number): Number of citations with PMID matches - `totalSubmitted` (number): Number of citations submitted - `totalWarnings` (number): Number of matched citations that carry at least one warning ### `pubmed_convert_ids` (~156 tokens) Pubmed Convert Ids Convert between article identifiers (DOI, PMID, PMCID). Accepts up to 50 IDs of a single type per request. Only resolves articles indexed in PubMed Central — for articles not in PMC, use pubmed_search_articles instead. Input parameters: - `idType` (string, required): The type of IDs being submitted. Required so the API can unambiguously resolve them. - `ids` (array, required): Article identifiers to convert. All IDs must be the same type. DOIs: "10.1093/nar/gks1195", PMIDs: "23193287", PMCIDs: "PMC3531190" (the "PMC" prefix is optional — bare digits like "3531190" are also… Output parameters: - `records` (array): Conversion results, one per input ID - `totalConverted` (number): Number of IDs successfully converted - `totalSubmitted` (number): Number of IDs submitted ### `pubmed_europepmc_search` (~551 tokens) Pubmed Europepmc Search Search Europe PMC, a broad open-access biomedical corpus. Surfaces preprints (`source: PPR`), patents (`source: PAT`), Agricola (`source: AGR`), plus everything in PubMed (`MED`) and PMC. Use when additional coverage is needed — preprints and EPMC-only OA records are the typical recovery. Paginate via `cursorMark`. Defaults to `MED`, `PMC`, and `PPR`; pass `sources` to include `PAT` / `AGR`. Abstracts arrive as a bounded `abstractSnippet` with `abstractTruncated` marking the cut ones — pass a hit’s `source` and `epmcId` to `pubmed_europepmc_fetch` for the complete abstract. Input parameters: - `cursorMark` (string): Pagination cursor. Use `*` (default) for the first page; pass the previous response's `nextCursorMark` for subsequent pages. - `pageSize` (integer): Results per page. Max 100 per EPMC API. - `query` (string, required): Europe PMC search query. Supports field tokens like `AUTH:""`, `JOURNAL:""`, `TITLE:"<words>"`, `PUB_YEAR:[2020 TO 2024]`, `DOI:"..."`, `EXT_ID:<pmid> AND SRC:MED`, `PMCID:PMC<digits>`.… - `resultType` (string): `core` returns abstract, IDs, dates, license; `lite` is a smaller payload with IDs and titles only. - `sort` (string): Optional EPMC sort: `<field> asc|desc`. Documented sortable fields: `P_PDATE_D` (publication date), `CITED` (citation count), `AUTH_FIRST` (first author surname), `PUB_YEAR` (publication year). Examp… - `sources` (array): Filter to specific EPMC sources. Defaults to MED, PMC, PPR when omitted. Pass an explicit array including PAT or AGR to broaden coverage. Allowed values: MED, PMC, PPR, PAT, AGR. Output parameters: - `appliedSources` (array): Sources the query was filtered against (defaults applied) - `cursorMark` (string): Cursor used for this response (echoed from the request) - `hits` (array): Matching Europe PMC records, in the order EPMC returned them - `nextCursorMark` (string): Cursor to pass back as `cursorMark` for the next page. Absent on the final page. - `notice` (string): Optional guidance when results are empty or paging overshot - `query` (string): Effective query string echoed by Europe PMC - `searchUrl` (string): Europe PMC's website search URL for this query - `totalCount` (number): Total matching records across all pages ### `pubmed_europepmc_fetch` (~201 tokens) Pubmed Europepmc Fetch Fetch complete Europe PMC records — including the full, untruncated abstract — for records addressed by `source` plus `epmcId`. Pairs with `pubmed_europepmc_search`, which returns bounded `abstractSnippet` values and flags cut ones with `abstractTruncated: true`; pass those hits' `source` and `epmcId` here to read the whole abstract. This is the retrieval path for preprint (`PPR`), patent (`PAT`), and Agricola (`AGR`) records, which frequently carry no PMID and no DOI, so `pubmed_fetch_articles` and `pubmed_fetch_fulltext` cannot address them. Up to 25 records per call. Input parameters: - `records` (array, required): Records to retrieve, each addressed by the `source` and `epmcId` of a `pubmed_europepmc_search` hit. The whole batch resolves in one Europe PMC request. Output parameters: - `notFound` (array): Requested `source` + `epmcId` pairs Europe PMC returned no record for - `notice` (string): Guidance when one or more requested records could not be resolved. Absent when every record came back. - `records` (array): Resolved records, in the order Europe PMC returned them ## Diagnostics Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/cyanheads-pubmed-mcp-server/pubmed#diagnostics ## Score history - 2026-08-03: 70 - 2026-08-02: 70 - 2026-08-01: 69 - 2026-07-31: 69 - 2026-07-30: 68 - 2026-07-28: 67 - 2026-07-27: 66 - 2026-07-26: 65 ## Links - Remote endpoint: https://pubmed.caseyjhand.com/mcp - Repository: https://github.com/cyanheads/pubmed-mcp-server - Changelog RSS feed: https://verifymcp.io/servers/cyanheads-pubmed-mcp-server/pubmed/changelog.xml - Changelog JSON feed: https://verifymcp.io/servers/cyanheads-pubmed-mcp-server/pubmed/changelog.json - HTML version of this page: https://verifymcp.io/servers/cyanheads-pubmed-mcp-server/pubmed