Bring Open Access
to Pydantic AI
Learn how to connect Zenodo to Pydantic AI and start using 14 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
GDPR Free for SubscribersCompatible with every major AI agent and IDE
Gemini
What is the Zenodo MCP Server?
Connect your Zenodo account to any AI agent to streamline your scientific research workflows and data management through natural conversation.
What you can do
- Deposition Management — Create new unpublished depositions, update metadata, and manage your research drafts directly from the AI.
- Record Discovery — Search and list public records across the entire Zenodo database to find relevant research, software, or datasets.
- File Inspection — List all files attached to specific depositions to understand the contents of a research package.
- Metadata Control — Precisely update titles, creators, descriptions, licenses, and access rights for your unpublished work.
- Version Tracking — Retrieve specific deposition details using unique IDs to monitor the status of your submissions.
How it works
- Subscribe to this server
- Enter your Zenodo Personal Access Token
- Start managing your research data from Claude, Cursor, or any MCP-compatible client
No more manual navigation through complex forms to update a dataset description or find a specific research record. Your AI acts as a dedicated research assistant.
Who is this for?
- Researchers & Academics — quickly draft depositions and manage metadata for publications without leaving your writing environment.
- Data Scientists — automate the listing and retrieval of datasets for analysis directly from your code editor.
- Open Science Advocates — easily search and discover public research artifacts to foster collaboration and transparency.
Built-in capabilities (14)
You can optionally provide metadata. Create a new Zenodo deposition
Note: Only unpublished depositions can be deleted. Delete an unpublished Zenodo deposition
Delete a file from a Zenodo deposition
Discard edits on a Zenodo deposition
Edit a published Zenodo deposition
Retrieve a Zenodo deposition by ID
Retrieve a published Zenodo record by ID
List files in a Zenodo deposition
List Zenodo depositions
Search published Zenodo records
Create a new version of a Zenodo deposition
WARNING: Once published, a deposition cannot be deleted. Publish a Zenodo deposition
Update a Zenodo deposition
Upload a text file to a Zenodo deposition
Why Pydantic AI?
Pydantic AI validates every Zenodo tool response against typed schemas, catching data inconsistencies at build time. Connect 14 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.
- —
Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application
- —
Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Zenodo integration code
- —
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
- —
Dependency injection system cleanly separates your Zenodo connection logic from agent behavior for testable, maintainable code
Zenodo in Pydantic AI
Zenodo and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Zenodo to Pydantic AI through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Zenodo in Pydantic AI
The Zenodo MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 14 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Pydantic AI only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Zenodo for Pydantic AI
Every tool call from Pydantic AI to the Zenodo MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I delete a deposition that has already been published?
No. The delete_deposition tool only works for unpublished depositions. Once a record is published on Zenodo, it is permanent to ensure scientific traceability.
How can I search for public datasets about a specific topic?
You can use the list_records tool with a search query. For example, ask the agent to 'Search Zenodo records for climate change' and it will return matching public entries.
Is it possible to see which files are included in a deposition before downloading them?
Yes! Use the list_deposition_files tool with the Deposition ID. The agent will provide a list of all filenames and metadata associated with that specific deposition.
How does Pydantic AI discover MCP tools?
Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.
Does Pydantic AI validate MCP tool responses?
Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.
Can I switch LLM providers without changing MCP code?
Absolutely. Pydantic AI abstracts the model layer. your Zenodo MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.
MCPServerHTTP not found
Update: pip install --upgrade pydantic-ai
Explore More MCP Servers
View all →
Feedly
12 toolsManage your news aggregation via Feedly — list collections, read streams, and search for feeds directly through your AI agent.
Stoplight
7 toolsConnect your AI to Stoplight. Design, document, and manage your API lifecycle, exploring workspaces and schemas effortlessly.
Markdown Task Extractor
1 toolsInstantly scan any local folder of Markdown notes (Obsidian, Notion, Logseq) and aggregate every scattered '- [ ]' to-do item into a single, structured list for your AI.
ClinicalTrials.gov
3 toolsSearch the world's largest registry of clinical research studies — covering diseases, drugs, and experimental therapies across all phases.