How to Use the Nuclino MCP in Pydantic AI

Q: How do I configure the Nuclino toolset in Pydantic AI?

You initialize MCPToolset with the HTTP endpoint provided by Vinkius. This registers the MCP Server directly, and you simply pass the toolset instance into your Agent constructor to expose all 12 tools instantly.

Q: Can I use Pydantic AI to safely delete Nuclino items?

Yes, but deleteitem requires explicit confirmation. The tool is designed to prevent autonomous agents from accidentally running destructive commands without human oversight.

Validate every Nuclino API response against strict type definitions at runtime using Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Nuclino MCP to Pydantic AI

Create your Vinkius account to connect Nuclino 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 Nuclino with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Wiki Querying via Pydantic AI

`get_item` retrieves the exact Markdown payload and configuration of a page, which Pydantic AI validates against your defined schemas at runtime. If the API returns unexpected metadata, the SDK raises a validation error immediately. This strict type-checking prevents silent data corruption in your production pipelines. You can safely pass workspace data to any language model, knowing the input structure is guaranteed to be correct.

Validated Workspace Mapping with MCP Server

`list_workspaces` returns internal workspace UUIDs that are essential for scoping subsequent queries. The framework parses these UUIDs directly into strongly-typed Python models, ensuring your agent never passes malformed parameters to other tools. The agent can then call `list_collections` to trace document relationship graphs or `list_users` to map human identities. Every single response is validated at the edge before your agent can act on it.

Safe Automated Document Writing

`create_item` builds permanent wiki pages using typed inputs, ensuring that headers, titles, and content structures match your schema rules. Your agent cannot write malformed Markdown that breaks your team's wiki layout. For existing pages, `update_item` applies partial edits safely. If your agent attempts to write an invalid property field, the runtime validation catches the error before the request ever hits your Nuclino workspace.

Setup guide

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

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

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

You initialize `MCPToolset` with the HTTP endpoint provided by Vinkius. This registers the MCP Server directly, and you simply pass the toolset instance into your `Agent` constructor to expose all 12 tools instantly.

The framework will immediately raise a validation error, halting the agent's execution. This prevents your code from processing unexpected null values or corrupted fields when calling tools like `list_fields`.

Yes, but `delete_item` requires explicit confirmation. The tool is designed to prevent autonomous agents from accidentally running destructive commands without human oversight.

No, Vinkius hosts and manages the MCP Server externally. Your Python code connects to the hosted endpoint over a secure, streamable HTTP connection, removing the need for local Node or Python runtimes.

All markdown payloads and item metadata are encrypted in transit and processed within a secure V8 isolate sandbox. No data is stored or cached on Vinkius infrastructure, maintaining a strict zero-trust boundary.

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