Bring Open Science
to Pydantic AI
Learn how to connect Figshare to Pydantic AI and start using 20 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 Figshare MCP Server?
Connect your Figshare account to any AI agent to streamline your research data management and publication workflows through natural conversation.
What you can do
- Article Management — List public articles, fetch specific article details, and create, update, or delete private articles in your account.
- File Handling — List files associated with articles, initiate multi-part S3 uploads, and track file details for your research datasets.
- Collections & Projects — Create and list public collections and projects to organize your scholarly output effectively.
- Metadata Control — Update titles, descriptions, and other metadata for your articles to ensure they are discoverable and well-documented.
How it works
- Subscribe to this server
- Enter your Figshare Personal Access Token
- Start managing your research repository from Claude, Cursor, or any MCP-compatible client
No more manual navigation through repository interfaces to check upload statuses or update metadata. Your AI acts as a research data manager.
Who is this for?
- Researchers & Academics — quickly upload datasets, update article descriptions, and check publication statuses without leaving your workspace.
- Data Managers — automate the organization of large collections and projects across institutional repositories.
- Librarians & Archivists — query public research outputs and manage metadata updates efficiently.
Built-in capabilities (20)
Complete a file upload
Create a new collection
Create a new private article
Create a new project
Delete an article
Get details of a specific article
Get total downloads for an article
Get total views for an article
Get custom metadata fields for the institution
Get file details
Get HR feed upload details
Initiate a file upload for an article
List files for an article
List public articles
List public collections
List public projects
Advanced search for articles
Advanced search for collections
Advanced search for projects
Update an existing article
Why Pydantic AI?
Pydantic AI validates every Figshare tool response against typed schemas, catching data inconsistencies at build time. Connect 20 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 Figshare integration code
- —
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
- —
Dependency injection system cleanly separates your Figshare connection logic from agent behavior for testable, maintainable code
Figshare in Pydantic AI
Figshare and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Figshare 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 Figshare in Pydantic AI
The Figshare 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 20 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
Figshare for Pydantic AI
Every tool call from Pydantic AI to the Figshare MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I upload files to a Figshare article using this integration?
Yes. You can use initiate_file_upload to start the process and complete_file_upload once the data transfer is finished. You can also use list_article_files to verify the contents of any article.
How do I create a new private draft for my research?
Simply ask the agent to use the create_private_article tool. Provide a title and an optional description, and the agent will generate a new private entry in your Figshare account.
Is it possible to organize my articles into projects or collections?
Absolutely. You can use create_project or create_collection to set up organizational structures, and use list_public_projects or list_public_collections to browse existing ones.
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 Figshare 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 →
Wiki.js
6 toolsManage your Wiki.js instance—create, search, and update documentation pages directly from your AI agent.
Orb
10 toolsAutomate usage-based billing via Orb — ingest events, manage subscriptions, and track invoices directly from any AI agent.
Chili Piper
10 toolsAutomate demand conversion via Chili Piper — manage concierge routes, distribution queues, and generate instant booking links directly from any AI agent.
CoinAPI
9 toolsUnified cryptocurrency data platform — access market data across hundreds of exchanges via AI.