crossref-mcp-server

Search Funders

crossref_search_funders

Read-only

Finds funders registered in the Crossref Funder Registry by name or funder DOI. Provide funder_doi for an exact single-funder lookup — the full DOI ("10.13039/100000001"), the bare registry ID ("100000001"), or either behind a doi: or https://doi.org/ prefix — or query for name-based search. Name-query results page with offset — the nextOffset enrichment carries the value for the following page, up to offset + rows = 100000. Set include_works to true to also return a page of the most recent works funded by the matched funder; that list pages two ways, in two orders. works_offset is the simple one: newest published first, capped ten times lower at works_offset + rows = 10000. works_cursor has no ceiling and reaches the whole funded-works list, newest registered first — ordered by the date each DOI was registered with Crossref, since Crossref does not walk a publication-date sort by cursor: pass works_cursor="*" on the first call, then chain the nextWorksCursor token from each response. The two cannot be combined, and a cursor walk always starts at the most recently registered work — it cannot resume from an offset. This list also counts works funded by the funder's registry descendants, which a crossref_search_works filter on {"funder": "10.13039/"} does not. Returns funder name, registry ID, country, and alternate names. The Funder Registry supersedes entries, and a deprecated one answers to the same names as its successor while carrying only a fraction of its works: such a record carries replacedBy with the superseding registry ID and the response carries a notice naming it. The replacement is never followed automatically — re-run with funder_doi set to that ID to get the current entry.

Input Schema

TableJSON Schema

Name	Required	Description
`rows`	No	Maximum funders to return for name queries, or works when include_works is true (1–100, default 10)
`query`	No	Funder name search query, e.g. "National Science Foundation" or "Wellcome Trust"
`offset`	No	Zero-based offset into the name-query funder list. Pass the nextOffset value from the previous response to continue. Ignored when funder_doi is set, which resolves exactly one record.
`funder_doi`	No	Funder DOI for exact lookup — the full DOI "10.13039/100000001" (NSF) or the bare registry ID "100000001". Supersedes query when provided.
`works_cursor`	No	Cursor token for deep paging of the funded-works list when include_works is true. Pass "*" to start the walk at the most recently registered work, then pass the nextWorksCursor value from each response. A walk runs by the date each DOI was registered with Crossref, newest first, not by publication date — Crossref does not walk a publication-date sort by cursor. Has no offset ceiling and cannot be combined with works_offset.
`works_offset`	No	Zero-based offset into the funded-works list when include_works is true. Pass the nextWorksOffset value from the previous response to continue. Capped at works_offset + rows = 10000; use works_cursor to read the whole list. Cannot be combined with works_cursor.
`include_works`	No	When true, also return a page of works funded by the matched funder. Requires an unambiguous funder — pass funder_doi when a name query matches more than one.

Output Schema

TableJSON Schema

Name	Required	Description
`error`	No	Present when the call failed. Absent on success.
`notice`	No	Guidance on a page that needs a caveat: a query nothing matched, an offset or works_offset past the end of a list that did match, a page that stops at one of the route offset ceilings with records still unretrieved, a returned funder that the Funder Registry has deprecated in favor of another entry, or a query or funder_doi supplied blank with nothing else to search by, so the page lists every funder unfiltered. Absent otherwise. A page needing more than one caveat carries them all in this one string.
`funders`	No	Matching funder records
`nextOffset`	No	Value to pass as offset on the next call for the following page of funders. Absent when this page ends the matches or the next page would breach the 100000-record offset ceiling.
`fundedWorks`	No	Page of works funded by the matched funder, newest first — by publication date on an offset page, by Crossref registration date on a works_cursor page. Only present when include_works is true.
`funderCount`	No	Number of funder records returned in this page
`fundersTotal`	No	Total funder records matching the query in Crossref
`nextWorksCursor`	No	Value to pass as works_cursor on the next call for the following page of funded works. Present only on a page requested with works_cursor, and absent once the walk reaches the end of the works list.
`nextWorksOffset`	No	Value to pass as works_offset on the next call for the following page of funded works. Absent when this page ends the works list, the next page would breach the 10000-record offset ceiling, or the page was requested with works_cursor.
`fundedWorksTotal`	No	Total count of funded works for the matched funder, when include_works is true

Schema Changelog

Changes observed during successful MCP inspections.

Changed9 schema fields changedSep 24, 2026

addedInput schema / properties / funder_doi / anyOf

Added value: +[
+  {
+    "const": "",
+    "type": "string"
+  },
+  {
+    "description": "Funder registry ID or funder DOI, e.g. \"100000001\"",
+    "pattern": "^(?:(?:https?:\\/\\/(?:dx\\.)?doi\\.org\\/|doi:)?10\\.13039\\/)?\\d+$",
+    "type": "string"
+  }
+]

removedInput schema / properties / funder_doi / pattern

Removed value: -"^(?:(?:https?:\\/\\/(?:dx\\.)?doi\\.org\\/|doi:)?10\\.13039\\/)?\\d+$"

removedInput schema / properties / funder_doi / type
```
Removed value: -"string"
```

changedInput schema / properties / rows / type

Previous value: -"number"New value: +"integer"

changedInput schema / properties / works_cursor / description

Previous value: -"Cursor token for deep paging of the funded-works list when include_works is true. Pass \"*\" to start the walk at the newest work, then pass the nextWorksCursor value from each response. Has no offset ceiling and cannot be combined with works_offset. Each token runs about 1500 characters and is returned on both result surfaces, a fixed cost per page — raise rows to spread it across more works on a long walk."New value: +"Cursor token for deep paging of the funded-works list when include_works is true. Pass \"*\" to start the walk at the most recently registered work, then pass the nextWorksCursor value from each response. A walk runs by the date each DOI was registered with Crossref, newest first, not by publication date — Crossref does not walk a publication-date sort by cursor. Has no offset ceiling and cannot be combined with works_offset."

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

Previous value: -"Machine-readable failure mode. Declared by this tool: `rate_limited`: Crossref answered HTTP 429 and the limit did not clear inside the retry budget. `upstream_unavailable`: Crossref was unreachable, returned a 5xx status, or served an HTML error page instead of JSON. `malformed_response`: Crossref returned HTTP 200 with a body that is not valid JSON. `request_timeout`: Crossref did not respond within CROSSREF_TIMEOUT_MS, or answered HTTP 408/504. `funder_not_found`: Funder DOI lookup returned 404 — funder is not in the Crossref Funder Registry. `ambiguous_funder`: include_works is true but the name query matched more than one funder, making the target ambiguous. `offset_too_large`: offset + rows exceeds the 100000-record ceiling Crossref allows on funder name search. `works_offset_too_large`: works_offset + rows exceeds the 10000-record ceiling Crossref allows on a funded-works list. `works_cursor_offset_conflict`: include_works is true and works_cursor was supplied alongside a works_offset above zero. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `rate_limited`: Crossref answered HTTP 429 and the limit did not clear inside the retry budget. `upstream_unavailable`: Crossref was unreachable, returned a 5xx status, or served an HTML error page instead of JSON. `malformed_response`: Crossref returned HTTP 200 with a body that is not valid JSON. `request_timeout`: Crossref did not respond within CROSSREF_TIMEOUT_MS, or answered HTTP 408/504. `invalid_cursor`: Crossref did not recognize the cursor token (HTTP 404 cursor-invalid). `invalid_parameter`: Crossref rejected a parameter value (a filter value of the wrong type or form), or answered HTTP 400 with a body that did not parse. `funder_not_found`: Funder DOI lookup returned 404 — funder is not in the Crossref Funder Registry. `ambiguous_funder`: include_works is true but the name query matched more than one funder, making the target ambiguous. `offset_too_large`: offset + rows exceeds the 100000-record ceiling Crossref allows on funder name search. `works_offset_too_large`: works_offset + rows exceeds the 10000-record ceiling Crossref allows on a funded-works list. `works_cursor_offset_conflict`: include_works is true and works_cursor was supplied alongside a works_offset above zero. Other values are possible when a failure originates below the handler."

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

Previous value: -[
-  "rate_limited",
-  "upstream_unavailable",
-  "malformed_response",
-  "request_timeout",
-  "funder_not_found",
-  "ambiguous_funder",
-  "offset_too_large",
-  "works_offset_too_large",
-  "works_cursor_offset_conflict"
-]New value: +[
+  "rate_limited",
+  "upstream_unavailable",
+  "malformed_response",
+  "request_timeout",
+  "invalid_cursor",
+  "invalid_parameter",
+  "funder_not_found",
+  "ambiguous_funder",
+  "offset_too_large",
+  "works_offset_too_large",
+  "works_cursor_offset_conflict"
+]

changedOutput schema / properties / fundedWorks / description

Previous value: -"Page of works funded by the matched funder, ordered by publication date (newest first). Only present when include_works is true."New value: +"Page of works funded by the matched funder, newest first — by publication date on an offset page, by Crossref registration date on a works_cursor page. Only present when include_works is true."

changedOutput schema / properties / notice / description

Previous value: -"Guidance on a page that needs a caveat: a query nothing matched, an offset past the end of a list that did match, a page that stops at one of the route offset ceilings with records still unretrieved, or a returned funder that the Funder Registry has deprecated in favor of another entry. Absent otherwise. A page needing more than one caveat carries them all in this one string."New value: +"Guidance on a page that needs a caveat: a query nothing matched, an offset or works_offset past the end of a list that did match, a page that stops at one of the route offset ceilings with records still unretrieved, a returned funder that the Funder Registry has deprecated in favor of another entry, or a query or funder_doi supplied blank with nothing else to search by, so the page lists every funder unfiltered. Absent otherwise. A page needing more than one caveat carries them all in this one string."

First observedSep 19, 2026

TDQS

A5/5.0

Behavior5/5

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

Annotations only declare readOnlyHint and openWorldHint, but the description goes far beyond that. It discloses intricate paging behaviors: the offset ceiling (offset + rows = 100000), the two works paging methods with their different ceilings (works_offset capped at 10000, works_cursor with no ceiling), the ordering rules (newest published first vs newest registered first), and why cursor uses registration date. It also explains deprecation handling (replacedBy, notice, no automatic following) and the descendant counting nuance. This is exemplary transparency.

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

Conciseness5/5

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

The description is long but every sentence carries essential information. It is logically organized: exact lookup, name paging, works inclusion with two paging methods, descendant behavior, deprecation handling. No filler or repetition. The critical constraints are front-loaded (exact vs query, paging ceilings) before deeper edge cases. It earns its length.

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?

For a tool with 7 parameters and two distinct paging schemes, the description covers every operational aspect: how to start a cursor walk ('*'), how to chain tokens, what happens when combining methods (cannot), what the offset ceilings are, how deprecation affects results, and what fields are returned. It even anticipates the confusion about publication vs registration date and the descendant inclusion difference. There is no missing piece an agent would need to call this tool correctly.

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

Parameters5/5

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

While schema descriptions cover all 7 parameters, the tool description adds substantial semantic value beyond them. For funder_doi it explains the accepted forms (full DOI, bare ID, with prefixes) and that it supersedes query. For works_cursor and works_offset it clarifies the ceiling difference, the ordering logic, and the mutual exclusivity. It also explains the include_works prerequisite. This goes well beyond the baseline for 100% schema coverage.

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?

The description opens with a precise statement: 'Finds funders registered in the Crossref Funder Registry by name or funder DOI.' This names the exact resource (Funder Registry) and the two lookup modes, immediately distinguishing it from sibling tools like crossref_search_works or crossref_search_journals. It also lists the returned fields (name, registry ID, country, alternate names), so an agent knows exactly what to expect.

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?

The description gives explicit guidance on when to use each mode: 'Provide funder_doi for an exact single-funder lookup' vs 'or query for name-based search.' It also explains when include_works is needed and the requirement for an unambiguous funder. Crucially, it contrasts with crossref_search_works: 'This list also counts works funded by the funder's registry descendants, which a crossref_search_works filter on {"funder": "10.13039/<id>"} does not.' This explicitly routes agents to the right tool for descendant works.

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

All crossref-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.