Can the AI perform destructive actions like making a real payment or deleting invoices?

No. The integration focuses strongly on extraction via READ endpoints (e.g. `list_payments`, `list_budgets`, `list_expense_claims`). It is designed to act as an advanced analytical viewing lens allowing you to query, organize, and monitor financial positions without executing operational mutations like transferring money.

How can the AI help me understand a specific expense claim?

You can provide the Expense ID from your `list_expense_claims` search and ask natural questions. The AI will pull the structured data and explain explicitly who submitted the reimbursement, the exact amount, the associated spending currency, and the current processing status, formatting it all into an easily digestible summary.

How deep is the Spendesk token scoped? Is it secure?

The integration is secure. Your Vinkius Agent runs strictly client-side on your PC. It queries the API using the explicit Bearer Token you manage. Spendesk's token access capabilities can also be carefully constrained natively from your Organization's Integration Settings to further enforce least privilege.

Spendesk MCP Server for Pydantic AI 9 tools — connect in under 2 minutes

Name: Spendesk
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 9 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Spendesk 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 Spendesk "
            "(9 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Spendesk?"
    )
    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 Spendesk MCP Server

Bring your Spendesk financial operations natively into your AI workspace. Eliminate constant tab switching to check the finance dashboard. You can now use conversational prompts to audit real-time company expenses, verify specific payment IDs, and inspect active supplier invoices while writing your integration code or managing operational scripts.

Pydantic AI validates every Spendesk tool response against typed schemas, catching data inconsistencies at build time. Connect 9 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

Track Cash Flow — Monitor organizational outflows by executing list_payments. Need deep details on a specific transaction? Pull exactly what happened using get_payment_details
Audit Invoices & Expenses — Keep track of pending vendor bills via list_invoices and review employee out-of-pocket reimbursements triggering list_expense_claims
Supplier Management — Check your registered vendor matrix using list_suppliers and pull contact or payment history directly calling get_supplier_details
Control Limits — Actively supervise remaining budget allocations calling list_budgets and watch the assigned corporate limits on issued plastic/virtual via list_cards

The Spendesk MCP Server exposes 9 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 Spendesk to Pydantic AI via MCP

Follow these steps to integrate the Spendesk 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 9 tools from Spendesk with type-safe schemas

Why Use Pydantic AI with the Spendesk MCP Server

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

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

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

Spendesk + Pydantic AI Use Cases

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

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

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

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

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

Spendesk MCP Tools for Pydantic AI (9)

These 9 tools become available when you connect Spendesk to Pydantic AI via MCP:

get_payment_details

Get detailed information about a specific payment

get_supplier_details

Get detailed information about a specific supplier

list_budgets

List all budgets and their spending status

list_cards

List all virtual and physical cards issued

list_expense_claims

List all employee expense claims and reimbursement requests

list_invoices

List all invoices pending or processed

list_members

List all team members with Spendesk access

list_payments

List all payments in the Spendesk account

list_suppliers

List all registered suppliers

Example Prompts for Spendesk in Pydantic AI

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

"Review Spendesk and show me all recent payments hitting our account."

"Bring a quick summary containing our currently monitored budgets to check for remaining allocated thresholds."

"Let's check our member list in Spendesk to see who holds what permission roles currently."

Troubleshooting Spendesk MCP Server with Pydantic AI

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

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Spendesk + Pydantic AI FAQ

Common questions about integrating Spendesk 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 Spendesk MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.