How to Use the CrossRef MCP in Mastra AI

Q: How do I add CrossRef tools to a Mastra AI agent?

Install @mastra/mcp@latest. Create a new client pointing to the Vinkius URL, then call mcpClient.listTools() and spread them into your agent's tool array.

Q: Does the CrossRef MCP Server require human approval in Mastra AI?

You can configure it that way. Just enable requireToolApproval in your setup. A human can review the exact DOI queries before the agent fires them off.

Automate academic literature reviews using Mastra AI workflows and the CrossRef database.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CrossRef MCP to Mastra AI

Create your Vinkius account to connect CrossRef to Mastra AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup CrossRef with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain academic searches with Mastra AI.

Literature reviews require systematic digging. You can build a Mastra AI workflow that takes a starting paper, grabs its metadata via `get_crossref_doi`, and then automatically searches for related works. The framework handles the sequence logic. If a query times out, the built-in exponential backoff tries again. You spread `mcpClient.listTools()` into your agent's configuration. The system manages the API limits and network hiccups while crunching through citations.

Map researcher networks automatically.

Tracking a scientist's output across institutions gets messy. The `search_crossref_author` tool pulls their entire publication history sorted by relevance. Your agent can loop through these results to find co-authors or track citation growth over time. Conditional branching makes this powerful. If the author search returns too many results, your workflow can automatically refine the query using specific years or journals. You get precise data without human intervention.

Search 140 million scholarly works with this MCP Server.

Finding niche scientific papers used to mean manually clicking through university library portals. Now you give the `search_crossref` tool a natural language prompt. It hits the world's largest DOI registry and returns full bibliographic data. This MCP Server plugs straight into your TypeScript backend. You initialize it with `new MCPClient()` and point it at the Vinkius endpoint. Mastra auto-detects the transport layer so you can focus on building the logic.

Setup guide

Set up CrossRef MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All CrossRef tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "crossref-mcp-client",
  servers: {
    "crossref-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "CrossRef Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to CrossRef tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent CrossRef transactions"
);
console.log(result.text);

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by CrossRef. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect CrossRef now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about CrossRef MCP in Mastra AI

Install `@mastra/mcp@latest`. Create a new client pointing to the Vinkius URL, then call `mcpClient.listTools()` and spread them into your agent's tool array.

Yes. The framework's workflow engine includes automatic retries with exponential backoff. Network blips during massive literature pulls will not crash your process.

You can configure it that way. Just enable `requireToolApproval` in your setup. A human can review the exact DOI queries before the agent fires them off.

It provides a relevance-sorted list of publications. Each entry includes citation counts, co-authors, and the publication year.

We operate on a zero-trust model using ephemeral sandboxes. The server processes your specific research queries and author names, then immediately destroys the environment. Your intellectual property stays private.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript