Xero API + MCP by Xero

# Fix list: Xero API + MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/xero, the October 2026 research run, assessed 1 October 2026. Grade B, 67.4 out of 100.

This is everything the published grade says the listing lacks, the biggest possible gain to the total first. It comes from the reason given for each score, the checklist each category was scored against (https://www.anchorterminal.com/benchmark/#checklist), the provenance checks, the deductions, what we couldn't check and what the review panel asked for. A fix counts at the next check, once it's public.

For a coding agent working on Xero API + MCP: work through the items below in the product, its docs and its public pages. Each category gives the reason for its score, with the points each checklist item earned, and the checklist itself, so the gap is the items that earned less than their points. Change the product, not the wording, and keep a note of what you changed and where it's published.

## 1. Payments & pricing, 35 out of 100, up to 8.1 more on the total

Why it scored 35: No x402, MPP or L402 (0). Tier prices are public in AUD (Core 35, Plus 245, Advanced 1,445 a month) with a per-GB egress overage of AUD 2.40, which we scored between plan-only and per-unit (15). Starter is free for 5 connections at 1,000 calls a day per organisation, with no card per the 30 September check, plus a Demo Company in any Xero account (20). Browser signup and an OAuth consent (0).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):

The published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).

- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.
- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for "contact sales" or prices behind a login.
- 20, a free tier or trial that doesn't need a card.
- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).

Payment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.

Open-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol.

## 2. Reliability, 68 out of 100, up to 6.4 more on the total

Why it scored 68: Statuspage at status.xero.com with product and region components (20). The feed covers 29 August to 1 October and holds 25 entries, mostly HMRC, ATO and Inland Revenue connections, US payroll and scheduled maintenance. None names the API, the longest product-side one was invoice email delays for 3.5 hours on 1 September, and global latency on 24 September lasted two minutes (20). Daily limits per organisation are published on the pricing page (1,000 on Starter, 5,000 above). The minute and concurrency limits are on a JavaScript-only page we couldn't read (10). The OpenAPI spec puts an Idempotency-Key parameter on 101 operations. 429 and Retry-After handling sits on the unreadable limits page (8). No SLA found (0). GA (10).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):

Hosted APIs, MCP servers, models and platforms.

- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).
- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.
- 15, rate limits documented with numbers.
- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.
- 10, an SLA published for any paid tier.
- 10, the surface agents use is generally available, not beta or preview.

Local packages, SDKs, frameworks and stdio MCP servers.

- 20, installs from an official package with supported runtimes stated.
- 25, a public CI and test suite, passing on the default branch.
- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).
- 15, semver discipline and breaking changes called out in a changelog.
- 15, version 1.0 or later, or declared stable.

Protocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors.

## 3. Security & auth, 64 out of 100, up to 6.3 more on the total

Why it scored 64: OAuth 2.0 with PKCE for public clients, client credentials for custom connections, 30-minute access tokens, and granular scopes such as accounting.invoices and accounting.reports.profitandloss.read required for apps created from 29 April 2026 (30). Read-only scopes make a read-only agent possible, and the MCP's XERO_SCOPES narrows the grant, but its delete tool carries no warning annotation (14). Returns ledger and contact text written by other people, with no injection guidance (3). No per-app audit view checked (0). ISO 27001:2022, SOC 2 reports, PCI DSS v4.0 and a vulnerability disclosure programme on the security page. security.txt returns 404 (17).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-security):

- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.
- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.
- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.
- 0 to 15, audit logs or per-call visibility for the operator.
- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.

Models are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing.

## 4. Agent ergonomics, 75 out of 100, up to 4.1 more on the total

Why it scored 75: The official MCP loads 51 tools with no toolsets or read-only subset. The API pages at up to 100 per page and honours If-Modified-Since (12). page, pageSize, where, order, Statuses and If-Modified-Since on list endpoints (20). Validation errors per element with `summarizeErrors`, though the MCP's mapped messages drop Xero's own error detail for the four common statuses (14). Idempotency-Key on 101 operations. The MCP sets no readOnlyHint or destructiveHint and includes a delete tool (14). SDKs for Node, Python, Java, .NET, PHP and Ruby, though every call needs the xero-tenant-id header (15).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):

- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).
- 20, pagination, filtering and output-size controls.
- 20, actionable, documented error responses, codes and messages an agent can recover from.
- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.
- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.

Models are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs.

## 5. Schema & documentation, 79 out of 100, up to 3.4 more on the total

Why it scored 79: OpenAPI specs for accounting, payroll, assets, files, bank feeds, projects and more in XeroAPI/Xero-OpenAPI, 235 operations in accounting alone (25). No llms.txt, and developer docs return "This app works with JavaScript enabled" to a fetch (0). MCP descriptions name the tool to call first ("can be obtained from the list-accounts tool") and explain ACCREC and ACCPAY, but don't say when not to use a tool (15). Zod schemas with enums, and enums throughout the spec (13). Examples in the spec, a `summarizeErrors` option for batch writes, and the MCP maps 401, 403, 404 and 429 to plain messages (11). Spec tagged 19.1.0 on 1 October and a dated developer changelog with deprecation dates (15).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):

APIs and MCP servers.

- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).
- 10, llms.txt or Markdown docs served for agents.
- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.
- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.
- 0 to 15, examples and documented error responses.
- 15, versioning and a public changelog.

Models are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference.

## 6. Transparency & trust, 75 out of 100, up to 2.2 more on the total

Made of editorial 60, provenance 90.

Why it scored 75: Closed API with developer terms dated 4 December 2025 naming Xero Limited (NZ 1830488) and the governing law by region. MIT MCP server and SDKs (17). Developer terms forbid training or fine-tuning AI models on API data. The UK privacy notice, dated 11 February 2025, says Xero uses AI and ML on its services and keeps data while there's a business or legal need, with no periods (15). Dated deprecations with 12 to 13 months' notice, such as accounting.transactions retiring on 13 September 2027 and XPM API v3.0 on 6 May 2027 (20). Transfers to Australia, New Zealand and the United States are named, with no public subprocessor list (8).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):

- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.
- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).
- 0 to 20, a deprecation policy or notices with dates.
- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).

The other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two.

Provenance checks not met in full (half of this category, computed from checked facts):

- security.txt: not found (0 of 10)

## 7. Maintenance & community, 76 out of 100, up to 2.1 more on the total

Why it scored 76: Xero-OpenAPI 19.1.0 on 1 October and xero-node 20.0.0 on 18 September (30). Six spec releases since 3 July and eight dated developer changelog entries between 16 July and 10 September (20). Closed API with a dated changelog and developer community. The MCP repository hasn't had a commit since 5 June (10). Current official SDKs in six languages, but the MCP isn't in the official registry and npm's latest is 0.0.17 from 26 May (12). The MCP repository has no CI workflows (4).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):

- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.
- 20, at least three releases or dated changelog entries in the last 90 days.
- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.
- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).
- 10, package health, current dependencies and CI.

Models are read for deprecation notice periods and model churn rather than release counts.

## What we couldn't check

What we couldn't read counted as absent. Publishing it on a page a plain HTTP fetch can read (not only in a browser) lets the next check count it.

- unchecked: per-minute and concurrency limits, 429 and Retry-After behaviour (JavaScript-only page)
- Whether Xero shows API changes per app in a record's history, which would count as an audit trail
- Whether npm 0.0.17 includes the 26 May error-formatter fix. Its gitHead isn't on the main branch
- Whether an SLA exists on Enterprise

## Weaknesses

- Developer docs, including the per-minute rate limits, only render with JavaScript
- 1,000 calls a day per organisation on the free tier, 5,000 on paid
- Official MCP server idle since 5 June 2026, with no CI, no annotations and no registry entry
- Prices in AUD only, and App Certification is needed above 50 connections
- No security.txt and no public subprocessor list

## What costs an agent a turn today

The notes we give agents before they call it. Each one is a workaround an agent shouldn't need.

- Send xero-tenant-id on every call. The token alone doesn't name the organisation
- A bill is an Invoice with Type ACCPAY, a sales invoice is ACCREC. There's no separate bills endpoint
- Send an Idempotency-Key on creates so a retry after a timeout doesn't post twice
- Use If-Modified-Since and pageSize up to 100 to stay inside 1,000 calls a day on Starter
- Set XERO_SCOPES to read scopes only when the agent shouldn't write. The MCP still lists its write and delete tools

## What the review panel asked for

- pass Xero's error detail through
- annotate the delete tool
- hide writes under read scopes
- publish a security.txt

## When it's done

Send what changed and where it's published as a dispute (https://www.anchorterminal.com/builders/#disputes, or `POST https://www.anchorterminal.com/api/v1/contact` with `"kind": "dispute"`). Disputes are answered in public, and the listing is checked again by the same checklist. Paying for an audit or a listing claim changes nothing here.