Nuclino MCP Server for Pydantic AI 12 tools — connect in under 2 minutes
Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Nuclino through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP
async def main():
# Your Vinkius token. get it at cloud.vinkius.com
server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
agent = Agent(
model="openai:gpt-4o",
mcp_servers=[server],
system_prompt=(
"You are an assistant with access to Nuclino "
"(12 tools)."
),
)
result = await agent.run(
"What tools are available in Nuclino?"
)
print(result.data)
asyncio.run(main())
* 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
About Nuclino MCP Server
Connect your Nuclino account to your AI agent and seamlessly interact with your company's unified workspace for knowledge, docs, and projects.
Pydantic AI validates every Nuclino tool response against typed schemas, catching data inconsistencies at build time. Connect 12 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.
What you can do
- Teams & Workspaces — Rapidly list all teams you are part of, and enumerate the nested workspaces and collections to understand your organization's hierarchy.
- Search & Query — Perform global fuzzy searches using
search_itemsto track down specific documents, notes, or project pages across the entire knowledge base. - Read Items & Files — Read the exact content configuration of any item (document) via
get_item, and list attachments or files uploaded to the platform. - Record Creation — Instantly create new items natively inside your workspace using natural language.
- Telemetrics — Enumerate members and structural fields within your Nuclino domain to keep the agent aware of context and owners.
The Nuclino MCP Server exposes 12 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect Nuclino to Pydantic AI via MCP
Follow these steps to integrate the Nuclino MCP Server with Pydantic AI.
Install Pydantic AI
Run pip install pydantic-ai
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token
Run the agent
Save to agent.py and run: python agent.py
Explore tools
The agent discovers 12 tools from Nuclino with type-safe schemas
Why Use Pydantic AI with the Nuclino MCP Server
Pydantic AI provides unique advantages when paired with Nuclino through the Model Context Protocol.
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 Nuclino integration code
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
Dependency injection system cleanly separates your Nuclino connection logic from agent behavior for testable, maintainable code
Nuclino + Pydantic AI Use Cases
Practical scenarios where Pydantic AI combined with the Nuclino MCP Server delivers measurable value.
Type-safe data pipelines: query Nuclino with guaranteed response schemas, feeding validated data into downstream processing
API orchestration: chain multiple Nuclino tool calls with Pydantic validation at each step to ensure data integrity end-to-end
Production monitoring: build validated alert agents that query Nuclino and output structured, schema-compliant notifications
Testing and QA: use Pydantic AI's dependency injection to mock Nuclino responses and write comprehensive agent tests
Nuclino MCP Tools for Pydantic AI (12)
These 12 tools become available when you connect Nuclino to Pydantic AI via MCP:
create_item
Triggers real-time replication creating permanent Wiki documentation. Write a brand new knowledge Item / Page into a Workspace
delete_item
Always confirm with the user heavily before destroying knowledge. Irreversibly delete a structural Nuclino Item
get_item
Retrieve the exact Markdown payload and configuration of an Item
list_collections
Used to trace the document relationship graph paths visually within a target Workspace. List Collections (grouping directories) segmenting a Workspace
list_fields
Used to understand standard taxonomy dimensions applicable against Items. Map customizable structured property fields globally binding a Team
list_files
Exposes pure URL bindings mapping binary data records back to object storage. List physical attachments explicitly bolted onto an Item
list_items
Used to enumerate top-level document UUIDs, titles, and creation metadata natively spanning a specific Workspace layer. List all standard knowledge items (pages) in a Workspace
list_teams
Use this as the entry point to discover available root organizational unit IDs traversing down into workspaces. List all organizational Teams the authenticated user belongs to
list_users
Enumerate human identities attached globally onto a Team
list_workspaces
Returns internal workspace UUIDs essential for scoping later item queries. List all isolated Workspaces mapped within a specific Team
search_items
Use to uncover unknown UUIDs. Execute an indexed semantic search globally across a Team
update_item
Alters the sync tree immediately appending new wiki edits. Overwrite active partial Markdown states inside a listed Item
Example Prompts for Nuclino in Pydantic AI
Ready-to-use prompts you can give your Pydantic AI agent to start working with Nuclino immediately.
"Search Nuclino for any documentation mentioning 'SSO Security Policies'."
"Create an item titled 'Project X Architecture Brief' in the Engineering workspace."
"List all teams connected to this authentication token."
Troubleshooting Nuclino MCP Server with Pydantic AI
Common issues when connecting Nuclino to Pydantic AI through the Vinkius, and how to resolve them.
MCPServerHTTP not found
pip install --upgrade pydantic-aiNuclino + Pydantic AI FAQ
Common questions about integrating Nuclino MCP Server with Pydantic AI.
How does Pydantic AI discover MCP tools?
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?
Can I switch LLM providers without changing MCP code?
Connect Nuclino with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect Nuclino to Pydantic AI
Get your token, paste the configuration, and start using 12 tools in under 2 minutes. No API key management needed.