Automation Anywhere

# Fix list: Automation Anywhere

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/automation-anywhere, the October 2026 research run, assessed 14 October 2026. Grade D, 50.9 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 Automation Anywhere: 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, 35 out of 100, up to 13 more on the total

Why it scored 35: Graded on the hosted Control Room API and MCP inbound. A public status site lists Control Room components by region with incident and maintenance history (20). The history we received showed maintenance notices and Enterprise Knowledge outages without dates, so the 90-day record of Control Room incidents could not be read (5). No rate limits found in the public Control Room API pages (0). No 429 or retry guidance found (0). No SLA found in the product-specific terms (0). The Control Room API is 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, 15 out of 100, up to 10.6 more on the total

Why it scored 15: No x402, MPP or L402 (0). No published prices for paid plans (0). Community Edition is free with no credit card required, but whether it includes API or MCP inbound access was not stated (15 of 20). A person signs up and an administrator creates the OAuth 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. Schema & documentation, 55 out of 100, up to 7.3 more on the total

Why it scored 55: Every Control Room serves Swagger at /swagger/, which needs a Control Room of one's own. The endpoint reference did not render in the pages we could fetch (15 of 25). llms.txt on the website covers marketing pages, and no Markdown docs or docs llms.txt were found (0). Overview pages describe each module's purpose and MCP tool pages say when to use each tool and what fails (10 of 20). MCP inbound variables are typed (String, Number, Boolean, List, Dictionary, DateTime, Record) and marked required or optional (9 of 15). The response code table lists only generic HTTP statuses, with tool troubleshooting notes (6 of 15). Versioned modules v1 to v4, dated deprecations and dated release notes (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.

## 4. Agent ergonomics, 60 out of 100, up to 6.5 more on the total

Why it scored 60: Three standard MCP tools plus the inbound tools an administrator adds, and DiscoverAutomation returns at most nine matches (22 of 25). Filtering, sorting and pagination documented for list endpoints (20). Generic HTTP statuses with no documented error bodies. GetAutomationResult returns error details for failed runs (9 of 20). No idempotency key or MCP tool annotations found, with 409 for duplicates (4 of 20). Two-step auth before calls, case-sensitive JSON names, and no official SDK found (5 of 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. Security & auth, 64 out of 100, up to 6.3 more on the total

Why it scored 64: OAuth 2.0 bearer tokens or Authentication API tokens, with users authenticated through OIDC or SAML. No scopes beyond `openid` were documented for MCP (20 of 30). RBAC privileges such as View my bots and Run my bots limit discovery and runs, and missing required variables are prompted from the user (12 of 20). AI Governance logs for MCP inbound exist, with no prompt-injection guidance found (4 of 15). Audit log events for agent connection changes and every MCP-triggered run, plus an Audit API (15). A vulnerability disclosure policy with optional compensation and ISO 27001 and SOC 2 claimed on the website. No security.txt (13 of 20).

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, 66 out of 100, up to 3 more on the total

Why it scored 66: Cloud build 53728 went out on 7 October 2026 (30). Dated updates on 16 September, 5 October and 7 October 2026 (20). Public release notes and a community forum. Support was not tested (10 of 15). No official SDK and no entry in the official MCP registry (3 of 15). No package to assess (3 of 10).

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, 73 out of 100, up to 2.4 more on the total

Made of editorial 59, provenance 86.

Why it scored 73: Closed service with published website terms, an Intelligent Automation Agreement and product-specific terms (15). The privacy policy, modified 1 April 2026, gives retention rules such as up to 90 days for support data. No DPA or subprocessor list was read (16 of 30). A written API deprecation policy with minimum support and notice periods, and dated end-of-life notices (20). Regions are listed on the status site. Subprocessors were not found (8 of 20).

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):

- Terms of service: read, states 5 of the 7 things a reader expects (8.3 of 10)
- Privacy policy: read, states 8 of the 8 things a reader expects, and has 1 clause that costs points (8 of 10)
- 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: the Control Room API endpoint reference and authentication details, which render only in a browser or behind a Control Room's /swagger/
- unchecked: pages under docs.automationanywhere.com/bundle/, which robots.txt disallows for our crawler. A search snippet of one such page said connecting MCP-aware agents was not generally available, which we could not confirm on an allowed page
- unchecked: dated incident history on status.automationanywhere.digital for the last 90 days
- unchecked: whether Community Edition includes Control Room API and MCP inbound access
- unchecked: a cloud SLA, DPA and subprocessor list

## Weaknesses

- No API rate limits, 429 handling or retry guidance found in the public Control Room API pages
- The published response code table lists only generic HTTP statuses, with no error bodies
- DiscoverAutomation and RunAutomation need an Enterprise licence with the Process Reasoning Engine, supported in the US and Europe only
- Cloud prices are not published and no SLA was found in the product-specific terms
- MCP OAuth requires manual client setup in the Control Room and supports only the Manual OAuth type in the client

## 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.

- Call DiscoverAutomation with a specific query such as `Discover automations to create invoice in SAP`. It returns at most nine matches
- Keep the job ID from RunAutomation and poll GetAutomationResult until the status leaves Running/InProgress
- Send either `X-Authorization` with a token from the Authentication API or `Authorization: Bearer` from OAuth, never both in one request
- Match the case of every JSON parameter name. The Control Room API treats names as case-sensitive
- Use the v4 WLM endpoints. Eight v3 WLM endpoints were deprecated in v.43 and end with v.46

## 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.