How do I get my Concur Client ID and Secret?

Register a new application in the SAP Concur Developer Portal. Once approved, you'll receive a Client ID and Client Secret.

What is the Refresh Token used for?

SAP Concur uses OAuth 2.0. The Refresh Token automatically generates short-lived access tokens without requiring manual login each time.

Can I submit an expense report via this integration?

The current version focuses on reading and listing data. Submit and approve capabilities may be added in future updates.

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

Name: SAP Concur
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 SAP Concur 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 SAP Concur "
            "(9 tools)."
        ),
    )

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

Connect your AI assistant to SAP Concur, the leading platform for expense management, travel, and invoice automation.

Pydantic AI validates every SAP Concur 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

Expense Tracking — List and inspect individual expenses including amounts, categories, and receipt metadata.
Report Status — Check approval status of any expense report.
User Profiles — Retrieve employee profile data including cost center and department.

The SAP Concur 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 SAP Concur to Pydantic AI via MCP

Follow these steps to integrate the SAP Concur 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 SAP Concur with type-safe schemas

Why Use Pydantic AI with the SAP Concur MCP Server

Pydantic AI provides unique advantages when paired with SAP Concur 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 SAP Concur integration code

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

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

SAP Concur + Pydantic AI Use Cases

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

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

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

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

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

SAP Concur MCP Tools for Pydantic AI (9)

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

get_expense

Retrieve detailed information about a specific expense

get_expense_report

Retrieve detailed information about a specific expense report

get_report_summaries

Calculate basic totals for a list of recent expense reports

get_user_profile

Retrieve the profile details of the currently authenticated Concur user

list_attendees

Retrieve a list of expense attendees (for business meals, etc.)

list_expense_reports

Retrieve a list of your expense reports from Concur

list_expense_types

Retrieve a list of valid expense types configured in your organization

list_expenses

Retrieve a list of your expenses from Concur

list_pending_expenses

Quickly list all expenses that have not yet been assigned to a report

Example Prompts for SAP Concur in Pydantic AI

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

"Show me my last 10 expenses in Concur."

"Get the status of expense report 'rep-8842'."

"Retrieve the profile for employee 'E-4545'."

Troubleshooting SAP Concur MCP Server with Pydantic AI

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

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

SAP Concur + Pydantic AI FAQ

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