Robocorp

# Fix list: Robocorp

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/robocorp, the October 2026 research run, assessed 14 October 2026. Grade B, 65.5 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 Robocorp: 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. Security & auth, 44 out of 100, up to 9.8 more on the total

Why it scored 44: Graded as a library. No credential of its own. robocorp.vault reads secrets from Control Room or a local file, and robocorp.log hides sensitive names and values (18 of 30). No least-privilege mode or approval step, and robots run with the user's desktop rights (5 of 20). Desktop and browser content is read back into tasks with no injection guidance found (4 of 15). robocorp.log writes a detailed log of each run with every call and its arguments, minus hidden values (11 of 15). No SECURITY.md or advisories in either repository, security dependency updates on 4 and 8 October 2026, and Sema4.ai's security pages unreadable (6 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.

## 2. Agent ergonomics, 59 out of 100, up to 6.7 more on the total

Why it scored 59: No tool definitions in context. Output size is controlled through robocorp.log settings rather than call parameters (15 of 25). Locators, timeouts and work item iteration, but little output filtering (12 of 20). Typed exceptions such as ElementNotFound, MultipleElementsFound and TimeoutException (14 of 20). No idempotency guidance. Work items fail with a BUSINESS type, documented as not to be retried, or an APPLICATION type (8 of 20). Sensible defaults, Python and Robot Framework keyword interfaces (10 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.

## 3. Schema & documentation, 65 out of 100, up to 5.7 more on the total

Why it scored 65: Graded as a library. Typed Python APIs with docstrings and keyword documentation at rpaframework.org. No machine-readable contract beyond the code (12 of 25). No llms.txt on rpaframework.org (404). The repository's agent skill and its api.md reference are Markdown written for coding agents. sema4.ai docs were unreadable (5 of 10). Keyword docs state purpose with arguments, rarely when not to use one (12 of 20). Type hints and enums on most keywords, some locator strings free-form (10 of 15). Examples throughout, and typed exceptions such as ElementNotFound (11 of 15). Dated changelogs per package and SemVer (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. Payments & pricing, 60 out of 100, up to 5 more on the total

Why it scored 60: The libraries are free and self-hosted, so 20 + 20 + 20 under the self-hosted rule. Control Room is the paid option, but its pricing on sema4.ai was behind a bot check and could not be scored. No payment protocol (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.

## 5. Transparency & trust, 65 out of 100, up to 3.1 more on the total

Made of editorial 56, provenance 73.

Why it scored 65: Apache-2.0 for both repositories (30). The libraries run locally. Sema4.ai's privacy policy and terms were behind a bot check, and rpaframework.org loads Google Analytics (8 of 30). Changelogs record removals and deprecations, with no deprecation policy found (10 of 20). No telemetry code in the libraries. rcc has a do-not-track setting whose default was not read (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):

- Status page: not found (0 of 10)
- security.txt: could not be fetched (0 of 10)

## 6. Reliability, 87 out of 100, up to 2.6 more on the total

Why it scored 87: Scored as local software. Official PyPI packages with Python 3.10 or later stated, robocorp up to 3.15 and rpaframework up to 3.14 (20). Public CI per package, with rpaframework's main and Windows workflows passing on master on 4 October 2026 and robocorp's master runs passing to 14 October (25). rpaframework has 35 open issues and pull requests and robocorp 9. Of rpaframework's 15 newest, 8 had no reply, including RPA.Windows and Java Access Bridge problems from 2024 (12 of 25). The README commits to SemVer and each package has a dated changelog (15). rpaframework is marked Production/Stable at 33.0.2 and robocorp is 3.1.4 (15).

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.

## 7. Maintenance & community, 81 out of 100, up to 1.7 more on the total

Why it scored 81: rpaframework 33.0.2 on 4 October 2026 (30). rpaframework 33.0.0, 33.0.1 and 33.0.2 and robocorp 3.1.2 to 3.1.4 since 23 August 2026 (20). Commits are frequent, but most new issues get no reply (12 of 25). Current official packages, no MCP server (10 of 15). Lockfiles, scheduled dependency checks and passing CI (9 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.

## 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: Control Room plans and pricing, Sema4.ai terms, privacy policy, security page and docs at sema4.ai, which answered with a bot check
- unchecked: whether rcc collects usage data by default
- unchecked: whether Control Room is still sold to new customers under the Robocorp name

## Weaknesses

- robocorp.com redirects to sema4.ai, which answered our reader with a bot check, so the docs, Control Room pricing and terms were not read
- The repository's own agent skill says the rcc release page blocks automated requests and asks the user to fetch the download link
- Of the 15 newest open rpaframework issues and pull requests, 8 had no reply, including Windows automation issues open since 2024
- No SECURITY.md in either repository and no published advisories
- rpaframework.org has no llms.txt and loads Google Analytics on its documentation pages

## 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.

- Install libraries with `pip install robocorp` and add `rpaframework` or `robocorp-windows` separately. robocorp-windows is not in the meta-package
- Use RPA.Windows or robocorp.windows on Windows only. On macOS or Linux use RPA.Desktop, which works by keyboard, mouse and image matching
- Ask the user for the rcc download link for their platform, because the release notes page blocks automated requests
- Run a task package with `rcc task run --robot robot.yaml --task "TASK NAME"` and read the final status as well as the log output
- Keep secrets in robocorp.vault or environment variables and register sensitive names with robocorp.log so they are hidden from logs

## 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.