How to Use the CrossRef MCP in Pydantic AI

Q: How do I integrate CrossRef with Pydantic AI?

Install pydantic-ai-slimmcp. Initialize an MCPToolset with your Vinkius HTTP endpoint, then pass it as toolsets=toolset to your Agent. Do not use the deprecated MCPServerHTTP class.

Enforce strict typing on academic searches with Pydantic AI and 140M+ scholarly records.

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 Pydantic AI

Create your Vinkius account to connect CrossRef to Pydantic 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Resolve DOIs with guaranteed runtime validation

The `get_crossref_doi` tool fetches the title, authors, journal, year, type, citation count, and abstract for any valid DOI. It targets specific academic records like 10.1038/nature12373 to pull exact metadata. Pydantic AI validates every piece of this returned data against your defined models. If the API omits an expected field or returns a string instead of an integer for the citation count, your agent fails loudly rather than silently corrupting your database.

Search 140M+ papers via the CrossRef MCP Server

Calling the `search_crossref` tool queries the largest DOI registry in the world. The tool returns structured bibliographic data and citation counts for scholarly works across all scientific disciplines. Because Pydantic AI is model-agnostic, you can route these search results through any local or cloud provider. You care about correctness, so the framework ensures the search payload matches your strict schema before the agent attempts to process it.

Fetch type-safe author publication histories

Your agent uses the `search_crossref_author` tool to locate papers by a specific writer. The results arrive sorted by relevance and include the current citation metrics for each publication. Setup is straightforward using the unified MCPToolset approach. You pass the toolset to your Agent, and it strictly enforces the expected response structure for every author query it runs.

Setup guide

Set up CrossRef MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "crossref-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to CrossRef tools.",
)

result = await agent.run("List recent CrossRef transactions")
print(result.output)

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 Pydantic AI

Install pydantic-ai-slim[mcp]. Initialize an MCPToolset with your Vinkius HTTP endpoint, then pass it as toolsets=[toolset] to your Agent. Do not use the deprecated MCPServerHTTP class.

Yes. If a requested DOI lacks an abstract or publication year, Pydantic AI will throw a validation error at runtime if your model requires those fields. This prevents incomplete data from entering your system.

The framework is completely model-agnostic. You can use OpenAI, Anthropic, Gemini, or even local models to analyze the academic metadata retrieved from the registry.

The tool provides the current citation count for each returned publication. Your agent can use these integers to rank papers or filter out works below a certain impact threshold.

Vinkius executes your DOI lookups and author queries inside a secure V8 Isolate Sandbox. The architecture requires only one endpoint token, and the ephemeral nature of the MCP Server connection ensures your specific literature searches vanish immediately after execution.

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