The world of AI is rapidly evolving, and at Xero, we’re committed to staying at the forefront of innovation. We’re thrilled to announce the launch of a Model Context Protocol (MCP) server specifically designed for accounting data, available as open-source on GitHub.
The Model Context Protocol (MCP) and Why It Matters
You’ve likely heard about large language models (LLMs) and their incredible capabilities. But to truly unlock their potential, LLMs need access to relevant, real-time data. That’s where the Model Context Protocol comes in.
MCP is a standardised way for LLMs to request and receive contextual information from external data sources. Think of it as a universal translator that allows AI to understand and interact with complex data, like the information available in a customer’s Xero.
Why is this important? Because without context, LLMs can generate inaccurate or irrelevant responses. MCP ensures that AI interactions are grounded in reality, leading to more reliable and practical applications.

Xero’s MCP Server: Bridging the Gap Between AI and Accounting
We’ve developed an MCP server that seamlessly integrates with Xero’s public API, allowing LLMs to interact with business data in a secure and efficient way. This means, as a developer of AI Agents, you can easily build a solution that helps customers streamline accounting tasks, gain valuable insights, and make smarter business decisions.
Here are a few ways that developers can use our MCP server to create innovative AI-powered solutions:
- Create invoices with LLM assistance: Imagine simply telling an LLM, “Create an invoice for [customer name] for [product/service] with a quantity of [number].” Our MCP server allows the LLM to pull relevant data from Xero and generate a draft invoice for you to review and send.
- Manage contacts effortlessly: LLMs can now assist in creating and updating contact information in Xero, saving you time and reducing errors.
- Unlock customer insights: AI can analyze your customer transaction data to reveal valuable insights into spending patterns, allowing you to tailor your offerings and improve customer satisfaction.
- Automate invoice management: LLMs can help categorize invoices, identify discrepancies, and even draft responses to customer inquiries, freeing up your time for more strategic tasks.
Open Source and Built for Developers
We believe in the power of collaboration, which is why we’ve made our MCP server open-source. Developers can explore the code, contribute to its development, and build innovative AI-powered applications that integrate with Xero. You can find the code on our GitHub repository.
This is just the beginning. We’re excited to see how our developer community will leverage our MCP server to create innovative AI-powered solutions that enhance the Xero ecosystem. We’re committed to providing developers with the tools and technology to push the boundaries of AI in accounting, and this launch represents a major step forward in that journey. Stay tuned for more updates as we continue to explore the possibilities of AI in accounting.
Learn more about MCP here.