Datacite

Search Dois

search_dois

Read-onlyIdempotent

Search DataCite-registered DOIs (research datasets, software, etc.). Filter by free-text query, resource type, year, publisher, or affiliation, and SORT by relevance, recency, citations, downloads, or views — e.g. "most-downloaded climate datasets" (sort=downloads), "newest genomics datasets" (sort=recent), "most-cited datasets on X" (sort=citations). Returns DOI, title, creators, publisher, type, year, and citation/download/view counts.

Input Schema

TableJSON Schema

Name	Required	Description
`page`	No	1-based page (default 1)
`sort`	No	Result ordering: relevance (default), recent (newest registered), oldest, published (newest publication year), citations (most-cited), downloads (most-downloaded), views (most-viewed).
`year`	No	Publication year
`query`	No	Free-text query (titles, descriptions, creators)
`page_size`	No	1-1000 (default 25)
`publisher`	No	Publisher name filter
`affiliation`	No	Creator affiliation
`resource_type`	No	Dataset \| Software \| Text \| Image \| Sound \| Other (case-sensitive)

Output Schema

TableJSON Schema

Name	Required	Description
`total`	Yes	Total number of DOIs matching the query
`results`	Yes	Array of DOI summary records
`returned`	Yes	Number of results returned in this page
`total_pages`	Yes	Total number of pages available

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedJun 24, 2026

addedInput schema / properties / sort

Added value: +{
+  "description": "Result ordering: relevance (default), recent (newest registered), oldest, published (newest publication year), citations (most-cited), downloads (most-downloaded), views (most-viewed).",
+  "enum": [
+    "relevance",
+    "recent",
+    "oldest",
+    "published",
+    "citations",
+    "downloads",
+    "views"
+  ],
+  "type": "string"
+}

Changed2 schema fields changedMay 22, 2026

addedInput schema / examples

Added value: +[
+  {
+    "query": "climate change temperature anomaly",
+    "resource_type": "Dataset",
+    "year": 2023
+  },
+  {
+    "page": 1,
+    "page_size": 50,
+    "publisher": "Zenodo",
+    "query": "machine learning",
+    "resource_type": "Software"
+  }
+]

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "results": {
+      "description": "Array of DOI summary records",
+      "items": {
+        "properties": {
+          "citation_count": {
+            "description": "Number of citations",
+            "type": [
+              "number",
+              "null"
+            ]
+          },
+          "creators": {
+            "description": "List of creator names",
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          "datacite_url": {
+            "description": "URL to DataCite commons page for this DOI",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "doi": {
+            "description": "Digital Object Identifier",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "download_count": {
+            "description": "Number of downloads",
+            "type": [
+              "number",
+              "null"
+            ]
+          },
+          "publisher": {
+            "description": "Publisher name",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "resource_type": {
+            "description": "General resource type (Dataset, Software, etc.)",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "title": {
+            "description": "Primary title of the resource",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "url": {
+            "description": "URL to the resource",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "view_count": {
+            "description": "Number of views",
+            "type": [
+              "number",
+              "null"
+            ]
+          },
+          "year": {
+            "description": "Publication year",
+            "type": [
+              "number",
+              "null"
+            ]
+          }
+        },
+        "required": [
+          "doi",
+          "title",
+          "creators",
+          "publisher",
+          "year",
+          "resource_type",
+          "url",
+          "citation_count",
+          "download_count",
+          "view_count",
+          "datacite_url"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "returned": {
+      "description": "Number of results returned in this page",
+      "type": "number"
+    },
+    "total": {
+      "description": "Total number of DOIs matching the query",
+      "type": "number"
+    },
+    "total_pages": {
+      "description": "Total number of pages available",
+      "type": "number"
+    }
+  },
+  "required": [
+    "total",
+    "total_pages",
+    "returned",
+    "results"
+  ],
+  "type": "object"
+}

First observedMay 12, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false. Description adds details on return fields and sort behavior, which is consistent and slightly extends 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?

Concise and well-structured: purpose first, then filters, sort examples, and return fields. Every sentence adds value.

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 rich schema, annotations, and output schema, description covers all essential aspects completely. No gaps.

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?

All 8 parameters are documented in schema with descriptions. Description adds concrete usage examples and explains sort options with real-world queries, going beyond schema.

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?

Description clearly states it searches DataCite-registered DOIs for research outputs, listing specific filters and sort options. It distinguishes itself from sibling tools like 'get_doi'.

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

Usage Guidelines4/5

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

Provides explicit guidance on filtering (query, resource type, year, etc.) and sorting with examples. Lacks explicit 'when not to use' but context is clear.

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

All Datacite 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.