Xero (Accounting) MCP Pack
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent โ or use 1-click editor setup below.
๐ก Paste the JSON block into your client's configuration file under mcpServers, then restart the application.
Xero (Accounting) MCP Pack
Part of Pipeworx โ an MCP gateway connecting AI agents to 1476+ live data sources.
| Tool | Description |
|---|---|
list_organisations | List the Xero organisations (tenants) the connected account can access, with tenant id, name, and type. Xero accounting is multi-tenant โ use this first to discover the tenant_id for a specific organisation, then pass it to the other accounting tools to target that org. |
list_invoices | List invoices and bills from a Xero accounting organisation. Returns compact invoice summaries (number, type, status, contact, dates, total, amount due, currency) for bookkeeping, accounts-receivable, and accounts-payable review. Supports Xero filter expressions and pagination. |
list_contacts | List contacts (customers and suppliers) from a Xero accounting organisation. Returns name, email, status, and customer/supplier flags. Use for accounting, bookkeeping, and accounts-receivable/payable workflows. Supports Xero filter expressions and pagination. |
get_profit_and_loss | Get the Profit and Loss (income statement) financial report from a Xero accounting organisation for an optional date range. Returns the structured Xero report (report name, date, and row sections covering revenue, expenses, and net profit). Use for financial reporting and bookkeeping analysis. |
list_accounts | List the chart of accounts from a Xero accounting organisation. Returns each account's code, name, type, class, and status. Use to understand an organisation's general ledger structure for bookkeeping and financial reporting. |
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
tools/list at https://gateway.pipeworx.io/xero/mcp returns the tools in the table
above plus the shared Pipeworx meta-tools โ ask_pipeworx,
discover_tools, search_within, remember/recall and the rest of the
gateway-wide set. So the tool count you see is larger than this table: a
single-pack endpoint currently lists roughly 30 shared tools alongside the
pack's own. The connection's initialize response states its exact scope, and
is the authoritative answer for a given day.
This is deliberate, not multiplexing by accident. The meta-tools are what let a
scoped connection answer a question this pack does not cover โ via
ask_pipeworx, which routes across the whole catalog โ without you adding a
second MCP server. There is currently no way to mount a pack endpoint without
them; if the extra schemas cost you more context than the routing is worth,
connect to the full gateway once rather than to several pack endpoints.
Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:
Both URLs reach the same gateway and the same 1476+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
Instead of calling tools directly, you can ask questions in plain English โ this works on the pack endpoint above as well as on the full gateway:
The gateway picks the right tool and fills the arguments automatically.
MIT
No reviews yet โ be the first to share how this listing worked for you.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/xero-3)<a href="https://allmcps.com/mcp/xero-3"><img src="https://allmcps.com/api/badge/xero-3?style=directory" alt="Xero on AllMCPs" /></a>