What authentication does Box use?

Box supports Client Credentials Grant (CCG) for server-to-server auth. Create a Custom App in the Box Developer Console, select 'Server Authentication (Client Credentials Grant)', and get the Client ID and Client Secret.

Can I search file contents?

Yes. The search_content tool uses Box's full-text search engine. It searches inside documents, presentations, spreadsheets, and PDFs.

Does it support metadata queries?

Yes. The query_metadata tool supports Box metadata queries using SQL-like syntax against metadata templates applied to files and folders.

Box MCP Server for Pydantic AI 7 tools — connect in under 2 minutes

Name: Box
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 7 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Box through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

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 Box "
            "(7 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Box?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* 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 Box MCP Server

Connect your Box enterprise account to any AI agent and manage cloud content through natural conversation.

Pydantic AI validates every Box tool response against typed schemas, catching data inconsistencies at build time. Connect 7 tools through the 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

Files — Upload, download, search, and manage file metadata and permissions
Folders — Navigate, create, and list folder contents with recursive traversal
Search — Full-text search across all content with metadata filters
Collaborations — Manage shared access, invitations, and permission levels
Metadata — Apply and query custom metadata templates on files and folders
Users — List enterprise users and manage group memberships

The Box MCP Server exposes 7 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 Box to Pydantic AI via MCP

Follow these steps to integrate the Box 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 7 tools from Box with type-safe schemas

Why Use Pydantic AI with the Box MCP Server

Pydantic AI provides unique advantages when paired with Box 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 Box integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Box connection logic from agent behavior for testable, maintainable code

Box + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Box MCP Server delivers measurable value.

Type-safe data pipelines: query Box with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Box tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Box and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Box responses and write comprehensive agent tests

Box MCP Tools for Pydantic AI (7)

These 7 tools become available when you connect Box to Pydantic AI via MCP:

create_folder

Default parent is root (ID "0"). Create a new folder

get_file_info

Get file details

get_folder_collaborations

List collaborators on a folder

get_folder_info

Get folder details

list_folder_items

Use folder ID "0" for the root. Returns names, sizes, types, and modified dates. List items in a Box folder

list_users

List enterprise users

search_content

Filter by file extensions (pdf,docx,xlsx) or ancestor folder. Searches inside documents. Search files and folders

Example Prompts for Box in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Box immediately.

"Search for all contracts expiring in Q2 2026."

"Who has access to the Board Reports folder?"

"List the 10 largest files in the Engineering folder."

Troubleshooting Box MCP Server with Pydantic AI

Common issues when connecting Box to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Box + Pydantic AI FAQ

Common questions about integrating Box MCP Server with Pydantic AI.

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 Box MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.