How to Use the Elsevier ScienceDirect MCP in Pydantic AI

Q: Does the server require specific Pydantic AI versions?

Use the pydantic-ai-slimmcp package. It provides the necessary tools to connect to the HTTP endpoint of this server.

Enforce strict data schemas in Pydantic AI agents when querying Elsevier ScienceDirect research databases.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Elsevier ScienceDirect MCP to Pydantic AI

Create your Vinkius account to connect Elsevier ScienceDirect 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 Elsevier ScienceDirect with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Pydantic AI runtime validation

Pydantic AI forces your agent to define exact models for every response. When you call `get_article_metadata`, the server output must match your schema. If the data is malformed, the agent stops. You get a clear validation error instead of silent, corrupted research data.

Safe article retrieval in Pydantic AI

Use `get_article` to pull text, but wrap it in your Pydantic models. This ensures your code only ever handles structured, clean strings. No more guessing what fields exist. If the API changes, your agent fails loud and early, protecting your downstream logic.

Check hosting permissions programmatically

Before you process a document, call `get_hosting_permissions`. It returns the embargo status for the specific content. Your agent logic can use this to decide whether to skip the file. It keeps your pipeline compliant and prevents wasted API calls.

Setup guide

Set up Elsevier ScienceDirect 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": {
        "elsevier-sciencedirect-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Elsevier ScienceDirect 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 Elsevier ScienceDirect. 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 Elsevier ScienceDirect 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 Elsevier ScienceDirect MCP in Pydantic AI

You define a Pydantic model for the tool response. If the data from ScienceDirect doesn't fit, the agent raises a validation error.

Yes. Since the MCP server is model-agnostic, you can swap between local or remote models without changing your tool definitions.

Access is managed via entitlement checks. The server only returns content your session is authorized to view.

Use the `pydantic-ai-slim[mcp]` package. It provides the necessary tools to connect to the HTTP endpoint of this server.

The connection uses a single endpoint token. The server handles all authentication, ensuring no raw keys are ever handled by your agent code.

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

Mastra AI sdk-typescript

Start using the Elsevier ScienceDirect MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Get started