CData Xero MCP: SQL Access, Connect AI vs. Open-Source
CData's two ways to give AI SQL access to Xero: an open-source, read-only server via JDBC, or the commercial Connect AI platform, compared for IT teams.
On this page +
If your team standardizes AI access to business systems around SQL rather than app-specific tool calls, CData is probably already on your radar. It shows up twice in the Xero MCP space, as two genuinely different products that are easy to conflate. One is a free, open-source, read-only server you run yourself. The other is a commercial cloud platform aimed at IT teams connecting Xero alongside hundreds of other sources. This post covers what each one actually is, what it costs, and which fits an IT or data team’s evaluation.
Compared in this post:
- The open-source CData Xero MCP server
- CData Connect AI (the commercial platform)
- How the two compare side by side
- Governing AI access across many data sources
What Xero SQL access means for AI
Most Xero MCP servers, Xero’s official one included, expose Xero as a set of entity-specific tools: get a contact, list invoices, create a bill. That model fits a developer building a specific integration, but it doesn’t fit a data team’s usual approach, which is standardizing access across many systems behind one query interface. CData’s answer is to expose Xero as SQL-queryable data instead: the same shape a data team already uses for a database, a data warehouse, or any other source they connect.
The open-source CData Xero MCP server
CDataSoftware/xero-mcp-server-by-cdata is a read-only MCP server that lets a client like Claude Desktop query Xero as SQL-queryable data. It wraps the CData JDBC Driver for Xero and exposes it through a simple MCP interface, so an assistant can retrieve live Xero data by asking in natural language. It’s explicitly read-only: there’s no create, update, or delete path, and CData’s own repository points teams to its commercial Connect AI platform if they need write capability.
CData’s open-source Xero MCP server is a local, read-only route built around SQL access through the CData JDBC driver.
The shape of it, once connected:
-- read-only, SQL-style access over the CData JDBC driver
SELECT Name, AmountDue
FROM Invoices
WHERE Status = 'AUTHORISED' AND AmountDue > 1000
ORDER BY AmountDue DESCThe catch is licensing: the MCP server code is free and open source, but it runs on top of CData’s JDBC Driver for Xero, which you register for separately (a trial license to start, or a paid license for production use). So “free server” is accurate but incomplete; the driver underneath it isn’t automatically free. Setup runs through cloning the repo, building with Maven, installing the JDBC driver, and pointing a connection file at your Xero account.
Choose it when: you’re comfortable running a local process, want genuinely read-only access with no write surface at all, and can license the JDBC driver.
CData Connect AI
CData Connect AI is a different product: a commercial, cloud-hosted MCP platform CData describes as giving AI assistants and agents connectivity, semantic context, and access control across hundreds of enterprise systems, with Xero being one of many possible sources rather than the sole focus. It’s built for IT and data teams that want one governed connection point for AI access across their whole stack, with identity-based security and OAuth/SSO integration, rather than per-application MCP servers to manage individually. Unlike the open-source server, this one writes: alongside query, insert, update, and delete are core operations, scoped per connected system under IT control. That’s a materially different access model from the read-only server above, not just a hosted version of it.
The open-source server depends on CData’s Xero connectivity layer; Connect AI packages that broader connector ecosystem into a managed platform.
Pricing: Standard is $99/month ($79/month billed annually), including one user and one data source; Growth is $199/month ($159/month billed annually), including access to more source tiers plus derived views; Business is custom, with pooled tool calls and enterprise features like SCIM and premium support. Additional users and data sources beyond each tier’s included amount are billed as add-ons (pricing as of August 2026).
Choose it when: Xero is one source among several you’re standardizing AI access to, you want a managed platform rather than a server you run and patch yourself, and you may need governed write actions, not just queries.
Comparing the two
| Open-source MCP server | CData Connect AI | |
|---|---|---|
| Model | Local process, SQL-style access via JDBC | Cloud platform, managed MCP endpoint |
| Write access | No, read-only by design | Yes, governed insert/update/delete under IT control |
| Cost | Free server + licensed JDBC driver | $99/mo Standard ($79/mo annual) to $199/mo Growth ($159/mo annual) to custom Business |
| Best for | Teams comfortable running and licensing their own server | IT/data teams standardizing AI access across many sources |
| Scope | Xero only, per install | Xero plus hundreds of other connectors on one platform |
Figures current as of August 2026; re-verify against CData’s own pages before relying on them, as this category changes monthly.
Governing AI access across many data sources
The reason CData shows up on an IT/data team’s shortlist at all is governance, not just SQL syntax: a team connecting AI to ten systems doesn’t want ten different auth models, ten different tool surfaces, and ten different places to check who accessed what. The two CData options land in different places on that governance question, though. The open-source server sidesteps write governance entirely by having no write path at all; it’s one install per system, with authentication and audit left to you. Connect AI centralizes auth and access control across multiple sources, and it’s designed for write actions to be part of that: scoped per source, under IT control, rather than wide open.
If the actual requirement is that writing stays architecturally impossible, not just governed, that’s a different bar than Connect AI is built to clear; the open-source server meets it by having no write path, and so does a hosted layer like Kipper. See how Kipper’s Xero MCP connector is architected read-only with per-user permissions and every question logged, for comparison: scoped to Xero’s supported operational records rather than an unrestricted SQL surface.
FAQ
What’s the difference between CData’s open-source Xero MCP server and CData Connect AI?
They’re separate products, often confused because both come from CData. The open-source server is a free, read-only MCP server that exposes Xero as SQL-queryable data through the CData JDBC Driver for Xero, run locally against a client like Claude Desktop. CData Connect AI is a commercial cloud platform: a managed, remote MCP endpoint for natural-language queries across Xero and hundreds of other sources, aimed at IT and data teams standardizing AI access.
Is the CData Xero MCP server free?
The server code itself is open source and free. What isn’t free is the CData JDBC Driver for Xero it depends on: you register for a trial or a paid license separately. So the honest answer is free server, licensed driver.
Is CData’s Xero MCP server read-only?
Yes, by design. The open-source server exposes Xero as read-only, SQL-queryable data with no write, update, or delete tools. CData’s own repository points to its commercial Connect AI platform for full read-write (CRUD) capability.
How much does CData Connect AI cost?
As of August 2026: Standard is $99/month ($79/month billed annually) with one user and one data source included; Growth is $199/month ($159/month billed annually) with access to more source tiers and derived views; Business is custom-priced with pooled tool calls and enterprise features. Additional users and data sources are billed as add-ons on top of each tier.
Can these CData options write to Xero?
Only one of them. The open-source server cannot: it’s read-only by design, with no write tools. CData Connect AI can: it supports governed insert, update, and delete actions alongside queries, scoped per source under IT control. So the open-source server is the strictly read-only option; Connect AI is not.
Want the full picture across all Xero MCP options? See Xero MCP servers compared, or the ultimate Xero MCP guide.
Want governed answers instead of SQL access? See Kipper’s Xero MCP connector.