Workato API + MCP by Workato

# Fix list: Workato API + MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/workato, the October 2026 research run, assessed 1 October 2026. Grade C, 58.3 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 Workato 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. Reliability, 58 out of 100, up to 8.4 more on the total

Why it scored 58: Statuspage at status.workato.com (20). 15 incidents since 1 July 2026, most of them single connectors (Salesforce, Box, QuickBooks, Databricks). The platform ones are an 18-minute disruption of the API Platform, web app and recipe triggers on 16 July, recipe jobs with long pauses failing from 15 to 20 July, and intermittent degradation of FileStorage, Data Tables and the API Platform for about 53 hours from 21 to 23 September (10). Developer API limits published per endpoint, for example 60 requests a minute on most jobs endpoints and 1 a second for repeat and cancel (15). No 429 or Retry-After guidance found, though every call takes an `x-correlation-id` (3). No public SLA found (0). Developer API and AIRO MCP are generally available (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.

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

Why it scored 35: No x402, MPP or L402 (0). Workato Pro bundles are public, $75 for 2,500 credits up to $1,275 for 50,000, but credit costs per capability aren't on that page and Enterprise is quoted (15). Workato Free is a one-time 50,000-credit grant with no card (20). A person signs up in the browser and creates an API client (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.

## 3. Agent ergonomics, 51 out of 100, up to 8 more on the total

Why it scored 51: AIRO MCP tool count isn't published. Tools are limited to what the client role allows, and tool-level RBAC for MCP servers went GA on 5 September 2026 (15). Offset pagination (`offset_job_id`, `prev`) and filters such as `status` and `rerun_only` (18). Error messages say what was wrong and how many items were allowed, and `err.item.not_found` is distinct from a permissions error (15). No tool annotations or idempotency keys found (0). No official SDK, and the base URL differs across ten hosts (3).

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.

## 4. Schema & documentation, 63 out of 100, up to 6 more on the total

Why it scored 63: No OpenAPI file. The Developer API MCP server builds tools from the endpoints in the client's role, and we didn't see their schemas (5). llms.txt per the 30 September check (10). One reference page per resource stating each endpoint's purpose (12). Parameters typed and documented with enums, for example job `status` of succeeded, failed or pending (11). Request and response examples, and endpoint-specific error messages such as "Maximum 25 jobs can be repeated in a single request" (13). A dated changelog and dated deprecations, but no version in the API path (12).

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.

## 5. Security & auth, 70 out of 100, up to 5.3 more on the total

Why it scored 70: API client bearer tokens limited by a role (an endpoint list) and project scopes, legacy full-access keys removed on 14 October 2025, and OAuth 2.0 for AIRO MCP (30). Roles, tool-level RBAC and verified user access, which runs MCP tools with each end user's own app credentials. No confirmation step before destructive tools found (16). Recipes return third-party data and we found no prompt-injection guidance (3). The activity audit log tags MCP actions "(via AIRO)" and job history is readable through the API (15). The trust centre needs JavaScript and showed us nothing, the linked security overview is dated January 2025, and there's no security.txt per the 30 September check. We couldn't confirm certifications (6).

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.

## 6. Maintenance & community, 60 out of 100, up to 3.5 more on the total

Why it scored 60: Newest changelog entry 9 September 2026 (30). 11 dated entries after 3 July 2026, including tool-level RBAC for MCP servers on 5 September (20). Public changelog and a support portal. We didn't test responses (10). No official SDK on npm or PyPI and no entry in the official MCP registry found (0). Nothing public to judge package health (0).

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.

## 7. Transparency & trust, 72 out of 100, up to 2.5 more on the total

Made of editorial 53, provenance 90.

Why it scored 72: Closed service under published terms (15). Privacy policy and a security overview PDF from January 2025. The trust centre didn't render for us, so retention periods and the DPA are unchecked (12). Dated deprecations with notice, legacy API keys rejected from 14 July 2025 and removed on 14 October 2025, and deprecated parameters marked in the reference (16). Nine data centres disclosed. Subprocessor list not read (10).

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)

## 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: certifications, subprocessors and retention on the trust centre, which needs JavaScript
- How many tools AIRO MCP lists and whether they carry annotations
- Credit cost per API call and per MCP tool call
- Whether failed recipe tasks consume credits

## Weaknesses

- No OpenAPI file and no official SDK on npm or PyPI
- 15 status incidents since 1 July 2026, including about 53 hours of degraded FileStorage and API Platform in September
- Base URL changes per data centre, ten hosts in all
- The Developer API manages recipes and jobs. App actions come from recipes or MCP tools you publish
- Trust centre needs JavaScript and the public security overview dates from January 2025

## 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.

- Use the base URL for the workspace's data centre, and app.trial.workato.com for Free or Pro
- Give the agent an API client whose role lists only the endpoints it needs. The MCP server exposes those as tools
- Repeat or cancel at most 25 jobs per call and no more than one call a second
- Send an `x-correlation-id` on each call so failures can be traced in support tickets
- Every action step in a recipe is a task, so collapse loops before running at volume

## What the review panel asked for

- a diffable OpenAPI file
- a static trust page
- confirmation on destructive tools

## 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.