How to Use the Zenodo MCP in Pydantic AI

Q: How do I search for Zenodo records using Pydantic AI?

Your agent calls listrecords to find published work. Because of the Pydantic validation, you're guaranteed that the resulting list structure is correct and usable by your application.

Q: What are the best practices for updating Zenodo content with Pydantic AI?

Always use getdeposition to retrieve the existing data first. This allows your agent to compare it against new inputs, ensuring that the subsequent updatedeposition call maintains structural integrity.

Q: How does Zenodo handle versioning when using Pydantic AI?

The newversiondeposition tool manages this. The type-safe nature means you know exactly what metadata fields are being added or changed in the new version.

Q: What if I need to delete an unpublished Zenodo deposition with Pydantic AI?

You must use deletedeposition on a draft. The system prevents this operation from running against live, published data, which is good for safety.

Ensure perfect Zenodo data handling with Pydantic AI's type safety.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Zenodo MCP to Pydantic AI

Create your Vinkius account to connect Zenodo 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 Zenodo with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Deposition Creation and Updates

When you need to start a new project, your agent calls `create_deposition` for the initial setup. If data needs refinement later on, use `update_deposition`. The Pydantic framework ensures that any returned metadata conforms exactly to your expected schema. If files change, upload them via `upload_deposition_file`. You can also create new versions using `new_version_deposition`, and the response structure validates every field.

Retrieving Zenodo Records with Guaranteed Structure

To pull existing data, call `get_record` or use `list_records`. The major benefit here is that if Zenodo returns a record, the Pydantic layer validates it immediately. You won't get hallucinated fields. Need to check file contents? Use `list_deposition_files` and pass the list through validation. This guarantees you know exactly what data structure you're working with.

Controlling Zenodo Publishing Workflow via MCP Server

The publishing process is tightly controlled: use `publish_deposition` when it’s locked down, or use `edit_deposition` if small changes are needed. Since the agent fails loudly on bad data, this keeps your production pipeline clean. If you need to start fresh, `discard_deposition` handles cleanup, making sure any accidental edits don't break your expected data model.

Setup guide

Set up Zenodo 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": {
        "zenodo-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Your agent calls `list_records` to find published work. Because of the Pydantic validation, you're guaranteed that the resulting list structure is correct and usable by your application.

Always use `get_deposition` to retrieve the existing data first. This allows your agent to compare it against new inputs, ensuring that the subsequent `update_deposition` call maintains structural integrity.

The `new_version_deposition` tool manages this. The type-safe nature means you know exactly what metadata fields are being added or changed in the new version.

You must use `delete_deposition` on a draft. The system prevents this operation from running against live, published data, which is good for safety.

This server handles scientific metadata (deposition records) and file content identifiers. The core data type being validated and managed by Pydantic is the structured, schema-defined record.

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