# Fix list: Remote From Anchor Terminal's listing at https://www.anchorterminal.com/tools/remote, the October 2026 research run, assessed 8 October 2026. Grade BB, 70.7 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 Remote: 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). Per-person monthly prices are public, such as Payroll at $29 per employee and EOR at $699, with no API charge found. We scored it between plan-only and per-unit, as for Deel (15). A seeded sandbox company and token are issued after an email verification, with no card, for 14 days. No free production plan was found on the pricing page (15). A person submits the sandbox form or signs in through a browser. MCP clients can self-register for OAuth, but a person still signs in (5). 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. Agent ergonomics, 57 out of 100, up to 7 more on the total Why it scored 57: The MCP tool list needs a signed-in Remote account, so its size wasn't read. The docs say a client sees only the tools its role allows. REST lists take `page_size` up to 100, with no field selection (12). 42 operations take `page` and `page_size`, with filters such as `status`, `email` and `employment_id`, and `sort_by` on eight (16). A missing scope returns 403 naming every scope that would work, and 422 bodies carry field errors, but the body shape differs between endpoints (15). No idempotency key. Employments accept an `external_id` for deduplication, and approve or decline transitions refuse a second call per the vendor's skill notes. MCP annotations weren't read (8). No general server SDK in any language. The Remote Flows SDK is a React package, and the CLI has binaries for two platforms (6). 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. Security & auth, 74 out of 100, up to 4.6 more on the total Why it scored 74: Customer tokens are named, scoped from a catalogue of 78 scopes, revocable and sent only in the `Authorization` header. The MCP server uses OAuth 2.0 with PKCE (S256) and dynamic client registration, with six `mcp:` scopes split into read and write (30). Customer tokens have a read-only preset, MCP write tools are limited to employee self-service and a time-off request still goes to a manager. A partner request that omits `scope` receives `all:write` (16). The remote-for-ai plugin's skills tell agents to treat MCP responses, webhook payloads and free-text fields as untrusted input. The API docs themselves carry no such guidance (10). The token list shows name, status, creator and date, and the MCP page says writes follow the product's audit flows. No log of API calls for the operator was found (5). ISO 27001, SOC 2 Type 2 and CSA STAR Level 1, a penetration test summary on request at trust.remote.com, and a security contact address. No security.txt and no bug bounty found (13). 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. Schema & documentation, 78 out of 100, up to 3.6 more on the total Why it scored 78: An OpenAPI 3.0 document answers at gateway.remote.com/v1/docs/openapi.json with 303 operations and 116 webhook events. We found it by trying the path, and no docs page we read links it (25). llms.txt and a Markdown copy of each page (10). Operation descriptions average about 940 characters, list the token types and scopes accepted, and deprecated operations name their replacement. Few say when not to use an endpoint (16). 301 enums and required fields throughout, but country-specific bodies are JSON Schemas fetched at run time, and some filters with fixed values are plain strings (10). 1,450 examples, with 422, 401 and 404 declared on most operations and 429 on 142. Error bodies come in several shapes (12). The path is versioned at /v1 and the spec's version is 0.1.0. The REST changelog the docs point to redirects to a ReadMe dashboard login, so no public changelog was read (5). 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. Transparency & trust, 68 out of 100, up to 2.8 more on the total Made of editorial 51, provenance 85. Why it scored 68: Editorial half only. Closed service under terms of use last updated 3 August 2026, with a section on AI clients and the MCP server. The plugin and CLI repositories are MIT. The Remote Flows SDK repository has no licence file (15). The privacy policy and a Data Processing Addendum with eleven schedules agree on roles, deletion or return at termination and no training of language models on personal data. Retention periods are in a policy available only on request (20). The spec and docs date individual deprecations, such as the time-off balance endpoint (February 2025) and the `company.manage` scope. No policy with notice periods or removal dates was found (8). AWS is named as host. The sub-processor list is for signed-in customers or on request at the Trust Centre, with 14 days to object to changes (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): - Terms of service: read, states 6 of the 7 things a reader expects, and has 2 clauses that cost points (5.1 of 10) - security.txt: not found (0 of 10) ## 6. Maintenance & community, 72 out of 100, up to 2.5 more on the total Why it scored 72: The newest dated release is Remote Flows SDK v1.60.0 on 8 October 2026. The REST API has no readable public changelog (30). The SDK shipped 12 tagged versions between 7 September and 8 October 2026, and the CLI shipped v0.1.2, v0.1.3 and v0.2.0 between 8 July and 28 September (20). Closed service. The docs give api-support@remote.com, and the changelog link for the REST API redirects to a login (6). The SDK and CLI are current, but there is no server SDK and the MCP server isn't in the official MCP registry (8). The SDK repository has CI, nightly end-to-end tests and Renovate. The CLI's source isn't public (8). 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. Reliability, 96 out of 100, up to 0.8 more on the total Why it scored 96: Graded on the hosted REST API at gateway.remote.com, with the MCP server at mcp.remote.com. status.remote.com on Better Stack has Website, Platform and API components with uptime figures (20). The incident history for August to October 2026 lists one incident, the website down on 19 August, and none on the API or Platform components (30). Limits are published as 300 requests a minute per company for customer tokens and 1,000 a minute per client ID for partners (15). Every response carries `x-ratelimit-count`, `x-ratelimit-remaining` and `x-ratelimit-reset`, and the spec's 429 schema points to `Retry-After`. There is no idempotency key, and retry guidance for writes is in the vendor's CLI skill notes, not the API docs (11). The terms of use warrant 99.5 per cent monthly uptime with a credit at Remote's discretion (10). The API is at /v1 with no beta label, and the MCP docs carry none (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. ## 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 REST API changelog. https://developer.remote.com/update/changelog redirects to a ReadMe dashboard login, and /changelog returns 404 - unchecked: the MCP tool list, its size and its annotations. The server returns 401 without a signed-in Remote account - unchecked: the Remote API Terms of Use at remote.com/api-terms-of-use. The page draws a PDF by script, and the file it loads is named as terms of service updated May 2024 - unchecked: the Customer Terms of Service, Local Terms and Order Form Terms tabs were not read in full - unchecked: the sub-processor list, which is at employ.remote.com/dashboard/processors for signed-in customers - unchecked: GitHub stars and open issues. The GitHub API refused us for its rate limit - unchecked: whether 429 responses carry `Retry-After`. The spec's schema says so and the rate limit page lists only the three `x-ratelimit` headers - unchecked: whether the sandbox request form asks for anything beyond an email address. We did not submit it - The OpenAPI document was found by trying gateway.remote.com/v1/docs/openapi.json. No docs page we read links it - The lead names Remote Technology, Inc. The terms of use are an agreement with Remote Europe Holding B.V., and the privacy policy calls Remote Technology, Inc. the group's holding company - The terms of use list 'automate' among things a user will not do to the Platform, in the same document that sets rules for AI clients and the MCP server. Recorded as a fact - The security page states 99.999 per cent uptime, the terms warrant 99.5 per cent, and the status page shows 99.993 per cent for the API component ## Weaknesses - The REST API changelog link in the docs redirects to a ReadMe dashboard login, so no public dated record of API changes was read - No idempotency key on writes. The vendor's own skill notes list creates for employments, time off, expenses and webhooks as unsafe to retry - A partner authorisation request that omits `scope` is issued `all:write`, per the scopes page - No general server SDK. The Remote Flows SDK is React, and the CLI ships as binaries for macOS on Apple Silicon and Linux x86_64 only - The sub-processor list sits behind a customer login, and remote.com has no security.txt ## 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. - Match the token prefix to the host. `ra_test_` works only on https://gateway.remote-sandbox.com and `ra_live_` only on https://gateway.remote.com - Stay under 300 requests a minute per company for customer tokens, shared by every token, and read `x-ratelimit-remaining` and `x-ratelimit-reset` (milliseconds) - Check for an existing record before retrying a create, or set `external_id` on employments and treat a 422 for a duplicate as success - Fetch the country form schema (`GET /v1/countries/{country_code}/{form}`) before writing employment data. Country codes are three-letter ISO - Use the REST API for unattended work. The MCP server needs a browser sign-in and its write tools cover employee self-service only ## 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.