biorxiv-mcp-server

Get Preprint Full Text

biorxiv_get_fulltext

Read-only

Retrieve a preprint's full text as best-effort Markdown, extracted from its rendered HTML article page. Reads the latest version unless one is requested (the version input, or a vN suffix on the DOI), confirms it via the details API, then fetches and extracts the body — abstract, sections, inline citation labels, and the reference list. Table cells are not on the article page: each table appears as its caption, and omittedTables names it with the URL that serves its cells. bioRxiv and medRxiv share the 10.1101/ DOI prefix, so server="both" (the default) resolves the DOI against both in parallel and the response reports which server answered. This is HTML-to-Markdown extraction, not structured JATS: section structure is approximate and not guaranteed. Long articles exceed a single response, so use offset and limit to page through them (the response reports totalChars, remainingChars, and hasMore); paging is cheap because the extracted article is cached per version for an hour after the first read, so only the first chunk pays for a fetch. Not every preprint has an extractable HTML page — some are PDF-only and some origins block programmatic access — in which case a fulltext_unavailable error routes you to biorxiv_get_preprint for the title, metadata, and current abstract. For a preprint that has been published in a journal, the journal's version may have richer full text elsewhere.

Input Schema

Name	Required	Description	Default
`doi`	Yes	Preprint DOI (e.g. 10.1101/2024.05.28.596311 or 10.64898/2026.05.07.723463). A doi.org or biorxiv.org/medrxiv.org article URL, a doi: prefix, or a .full suffix is accepted and stripped; a trailing vN (…596311v2) requests that version. Without one, the latest version is resolved automatically.
`limit`	No	Maximum number of characters to return in this chunk. Default 20,000; a value past the remaining text returns the rest of the article. Check the length field for the actual count returned.
`offset`	No	Character offset into the full extracted text at which to start reading. 0 returns the beginning. To read the next chunk, use offset = prior_offset + prior_length (the length field from the previous response).
`server`	No	Server the preprint was posted on. "both" (default) checks bioRxiv and medRxiv in parallel to resolve the DOI — the full-text fetch itself only ever targets whichever server resolved, and the output server field names it.	both
`version`	No	Preprint version to read (1, 2, …) — the revision numbers biorxiv_get_preprint lists. Omit for the latest version. Must match a vN suffix on the DOI when both are given.

Output Schema

Name	Required	Description
`cap`	No	The limit (max characters) applied to this chunk.
`doi`	No	The resolved preprint DOI, in bare form.
`error`	No	Present when the call failed. Absent on success.
`shown`	No	Characters returned in this chunk.
`title`	No	Article title detected during extraction. Absent when the page exposed none.
`length`	No	Number of characters returned in this chunk.
`notice`	No	Paging guidance when the content was truncated — how to fetch the next chunk.
`offset`	No	Character offset into the full extracted text where this chunk begins.
`server`	No	Server the preprint was resolved on.
`content`	No	The requested chunk of full text as best-effort Markdown extracted from the rendered HTML page. Section structure is approximate — this is not JATS.
`hasMore`	No	True when more text follows this chunk. When true, call again with offset = offset + length.
`version`	No	Preprint version whose full text was retrieved — the requested one, or the latest revision when none was requested. Pass it back as version when paging.
`sourceUrl`	No	The full-text HTML page the content was extracted from.
`truncated`	No	True when this chunk was capped by limit and more text remains.
`wordCount`	No	Approximate word count of the FULL extracted article, not just the returned chunk — whitespace-delimited tokens of the same Markdown text that totalChars measures, so Markdown markers such as # and - count too.
`totalChars`	No	Total characters in the full extracted text. Use with offset and length to page through long articles.
`contentFormat`	No	How content was produced: Markdown extracted from the rendered HTML article page (constant).
`omittedTables`	No	Tables the article page names without their cells — content keeps each one's caption, and the cells live on a separate page at url. The same list on every chunk. Absent when the article has none.
`remainingChars`	No	Characters remaining after this chunk (totalChars - offset - length). 0 means this chunk reaches the end.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 18, 2026

changedOutput schema / properties / error / properties / data / properties / reason / description

Previous value: -"Machine-readable failure mode. Declared by this tool: `invalid_doi_format`: The input DOI does not match the 10.NNNN/ pattern, even after URL, doi:, and suffix stripping. `version_conflict`: The DOI carries a vN suffix and the version input names a different version. `version_not_found`: The preprint exists but has no revision with the requested version number. `doi_not_found`: The DOI resolves to an empty collection on every attempted server. `upstream_unavailable`: No attempted server resolved the DOI and at least one lookup failed against api.biorxiv.org. `rate_limited`: Either origin returned HTTP 429 for this host — the article page (www.biorxiv.org / www.medrxiv.org) during the full-text fetch, or api.biorxiv.org during version resolution. `fulltext_unavailable`: The preprint exists but its full-text HTML page is blocked, missing, or yields no extractable text (PDF-only). `offset_out_of_range`: offset is greater than or equal to the total character length of the extracted text. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `invalid_doi_format`: The input DOI does not match the 10.NNNN/ pattern, even after URL, doi:, and suffix stripping. `version_conflict`: The DOI carries a vN suffix and the version input names a different version. `version_not_found`: The preprint exists but has no revision with the requested version number. `doi_not_found`: The DOI resolves to an empty collection on every attempted server. `upstream_unavailable`: No attempted server resolved the DOI and at least one lookup failed against api.biorxiv.org; the version lookup used most of the call's time budget, so the article page was never requested or had not answered when the budget ran out; or the article page (www.biorxiv.org / www.medrxiv.org) did not answer within the call. `rate_limited`: Either origin returned HTTP 429 for this host — the article page (www.biorxiv.org / www.medrxiv.org) during the full-text fetch, or api.biorxiv.org during version resolution. `fulltext_unavailable`: The preprint exists but its full-text HTML page is blocked, missing, or yields no extractable text (PDF-only). `offset_out_of_range`: offset is greater than or equal to the total character length of the extracted text. Other values are possible when a failure originates below the handler."

Changed3 schema fields changedOct 15, 2026

changedInput schema / properties / limit / description

Previous value: -"Maximum number of characters to return in this chunk. Default 20,000; increase toward 50,000 for large context windows. Check the length field for the actual count returned."New value: +"Maximum number of characters to return in this chunk. Default 20,000; a value past the remaining text returns the rest of the article. Check the length field for the actual count returned."

changedInput schema / properties / limit / maximum

Previous value: -50000New value: +9007199254740991

addedOutput schema / properties / omittedTables

Added value: +{
+  "description": "Tables the article page names without their cells — content keeps each one's caption, and the cells live on a separate page at url. The same list on every chunk. Absent when the article has none.",
+  "items": {
+    "additionalProperties": false,
+    "description": "One table whose cells content does not include.",
+    "properties": {
+      "label": {
+        "description": "The table label as the article prints it, e.g. \"Table 1\".",
+        "type": "string"
+      },
+      "url": {
+        "description": "The article origin's page that serves this table's cells. Not fetched by this tool.",
+        "type": "string"
+      }
+    },
+    "required": [
+      "label",
+      "url"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

Changed8 schema fields changedSep 23, 2026

changedInput schema / properties / doi / description

Previous value: -"Preprint DOI (e.g. 10.1101/2024.05.28.596311 or 10.64898/2026.05.07.723463). The latest version is resolved automatically."New value: +"Preprint DOI (e.g. 10.1101/2024.05.28.596311 or 10.64898/2026.05.07.723463). A doi.org or biorxiv.org/medrxiv.org article URL, a doi: prefix, or a .full suffix is accepted and stripped; a trailing vN (…596311v2) requests that version. Without one, the latest version is resolved automatically."

addedInput schema / properties / version

Added value: +{
+  "description": "Preprint version to read (1, 2, …) — the revision numbers biorxiv_get_preprint lists. Omit for the latest version. Must match a vN suffix on the DOI when both are given.",
+  "maximum": 9007199254740991,
+  "minimum": 1,
+  "type": "integer"
+}

changedOutput schema / anyOf

Previous value: -[
-  {
-    "not": {
-      "required": [
-        "error"
-      ]
-    },
-    "required": [
-      "doi",
-      "server",
-      "version",
-      "content",
-      "contentFormat",
-      "sourceUrl",
-      "offset",
-      "length",
-      "totalChars",
-      "remainingChars",
-      "hasMore"
-    ]
-  },
-  {
-    "required": [
-      "error"
-    ]
-  }
-]New value: +[
+  {
+    "not": {
+      "required": [
+        "error"
+      ]
+    },
+    "required": [
+      "doi",
+      "server",
+      "version",
+      "content",
+      "contentFormat",
+      "wordCount",
+      "sourceUrl",
+      "offset",
+      "length",
+      "totalChars",
+      "remainingChars",
+      "hasMore"
+    ]
+  },
+  {
+    "required": [
+      "error"
+    ]
+  }
+]

changedOutput schema / properties / doi / description

Previous value: -"The resolved preprint DOI."New value: +"The resolved preprint DOI, in bare form."

changedOutput schema / properties / error / properties / data / properties / reason / description

Previous value: -"Machine-readable failure mode. Declared by this tool: `invalid_doi_format`: The input DOI does not match the 10.NNNN/ pattern. `doi_not_found`: The DOI resolves to an empty collection on every attempted server. `upstream_unavailable`: No attempted server resolved the DOI and at least one lookup failed against api.biorxiv.org. `rate_limited`: Either origin returned HTTP 429 for this host — the article page (www.biorxiv.org / www.medrxiv.org) during the full-text fetch, or api.biorxiv.org during version resolution. `fulltext_unavailable`: The preprint exists but its full-text HTML page is blocked, missing, or yields no extractable text (PDF-only). `offset_out_of_range`: offset is greater than or equal to the total character length of the extracted text. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `invalid_doi_format`: The input DOI does not match the 10.NNNN/ pattern, even after URL, doi:, and suffix stripping. `version_conflict`: The DOI carries a vN suffix and the version input names a different version. `version_not_found`: The preprint exists but has no revision with the requested version number. `doi_not_found`: The DOI resolves to an empty collection on every attempted server. `upstream_unavailable`: No attempted server resolved the DOI and at least one lookup failed against api.biorxiv.org. `rate_limited`: Either origin returned HTTP 429 for this host — the article page (www.biorxiv.org / www.medrxiv.org) during the full-text fetch, or api.biorxiv.org during version resolution. `fulltext_unavailable`: The preprint exists but its full-text HTML page is blocked, missing, or yields no extractable text (PDF-only). `offset_out_of_range`: offset is greater than or equal to the total character length of the extracted text. Other values are possible when a failure originates below the handler."

changedOutput schema / properties / error / properties / data / properties / reason / examples

Previous value: -[
-  "invalid_doi_format",
-  "doi_not_found",
-  "upstream_unavailable",
-  "rate_limited",
-  "fulltext_unavailable",
-  "offset_out_of_range"
-]New value: +[
+  "invalid_doi_format",
+  "version_conflict",
+  "version_not_found",
+  "doi_not_found",
+  "upstream_unavailable",
+  "rate_limited",
+  "fulltext_unavailable",
+  "offset_out_of_range"
+]

changedOutput schema / properties / version / description

Previous value: -"Preprint version whose full text was retrieved (the latest revision)."New value: +"Preprint version whose full text was retrieved — the requested one, or the latest revision when none was requested. Pass it back as version when paging."

changedOutput schema / properties / wordCount / description

Previous value: -"Approximate word count of the FULL extracted article as reported by the extractor (not just the returned chunk). Absent when the extractor reported none."New value: +"Approximate word count of the FULL extracted article, not just the returned chunk — whitespace-delimited tokens of the same Markdown text that totalChars measures, so Markdown markers such as # and - count too."

First observedSep 19, 2026

TDQS

A4.6/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Rich beyond annotations: HTML-to-Markdown not JATS, approximate section structure, per-version one-hour cache, offset/limit paging with totalChars/hasMore, table cells omitted with omittedTables URLs, and parallel server resolution. Annotations already declare readOnly/openWorld, so safety needs no restating. Slightly docks for not stating return shape explicitly, though output schema may cover it.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core action, then progressively elaborates paging, caching, and failure modes. Dense but every clause carries meaning; long, yet justified by a 5-param tool with several caveats.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given an output schema exists and return values needn't be re-explained, the description is complete: it covers extraction fidelity, paging, caching, table-cell omission, error routing, and version handling — everything an agent needs to call and interpret it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3; the description adds value by explaining offset/limit paging strategy, the caching that makes paging cheap, version resolution order, and the server='both' parallel resolution. Much is duplicative of the schema, keeping it below 5.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Retrieve a preprint's full text as best-effort Markdown') plus the extraction method, and explicitly distinguishes itself from biorxiv_get_preprint (metadata/abstract) and the journal's version. An agent can tell exactly what this returns vs. siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit routing: fulltext_unavailable error -> use biorxiv_get_preprint; published preprints -> journal version may be richer elsewhere. Covers the PDF-only/blocked-origin exclusions and when to page with offset/limit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All biorxiv-mcp-server tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.