# Fix list: Similarweb From Anchor Terminal's listing at https://www.anchorterminal.com/tools/similarweb, the October 2026 research run, assessed 8 October 2026. Grade D, 46 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 Similarweb: 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 as a hosted service, on the V5 REST API and the hosted MCP server. No public status page found, and similarweb.statuspage.io redirects to a login (0). No readable incident history (5). Rate limits published, 10 requests a second for REST and 20 pending requests for Batch (15). 429 is documented with advice to add a rate limiter and errors aren't charged, but no Retry-After or backoff guidance was found, and Batch has a retry endpoint (5 of 15). The SLA page is dated January 2016 and its PDF returns 404 (0). V5 is announced as live and carries no beta label (10). Total 35. 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, 5 out of 100, up to 11.9 more on the total Why it scored 5: No x402, MPP or L402 found (0). No price per credit or API plan price is public. The credit cost per endpoint and the formula are published, which earns 5 of 20 as a departure from the checklist. No free tier or API trial, since the FAQ requires an active subscription (0). A person has to buy through sales and an admin has to create the key (0). Total 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. ## 3. Security & auth, 52 out of 100, up to 8.4 more on the total Why it scored 52: Revocable API keys created by admins, with up to 3 per user, no expiry and credit caps per user, plus OAuth with PKCE and a `read` scope on the MCP server (22 of 30). Less 10 because the capabilities endpoint documents the key in a `?api_key=` query string. Data access is read-only and follows the plan's data sets and countries (14 of 20). No guidance found on untrusted content in returned URLs, keywords and app details (8 of 15). The keys table shows last use and monthly usage per key, and a credit dashboard shows usage by user (8 of 15). SOC 2 Type II and ISO 27001 stated, no security.txt, and the trust centre refused our reader (10 of 20). Total 52. 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, 63 out of 100, up to 6 more on the total Why it scored 63: No public OpenAPI file found. Reference pages carry structured parameter and response definitions in Markdown, and the MCP tool schemas need a key to read (8 of 25). llms.txt on both docs sites with Markdown pages (10). Endpoint pages state purpose, output fields, constraints and credit cost, with little on when not to use one (12 of 20). Parameters are typed with enums for granularity and device, and defaults are stated (12 of 15). Request and response examples exist, and the error table has mismatched descriptions for codes 101 and 102 (9 of 15). Versioned paths and two changelogs, the newer one unreadable to us (12 of 15). Total 63. 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. Maintenance & community, 33 out of 100, up to 5.9 more on the total Why it scored 33: The V5 docs version shows a publish date of 24 September 2026 in the page data, and the migration guide dates the legacy endpoint deprecation at 6 October 2026. This is documentation metadata, not a changelog entry, so 20 of 30. Three dated entries in 90 days not established, because the V5 changelog didn't load (0). Two public changelogs and a help centre with ticket support (8 of 15). No official SDKs, and the official MCP registry lists only third-party Similarweb servers (0). The hosted MCP server and both docs sites are live and current (5 of 10). Total 33. 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. ## 6. Agent ergonomics, 67 out of 100, up to 5.4 more on the total Why it scored 67: V5 requests name the metrics wanted and take `limit`, so responses can be sized. The MCP tool count couldn't be read without a key, and the vendor cites more than 75 endpoints (15 of 25). `limit`, `offset`, `sort` and `asc` plus country, date and granularity filters (20). Errors are a short documented table with `error_code` and `error_message` in responses, and 401 is used for data not found (10 of 20). The data endpoints are reads, so retries are safe, and the MCP scope is `read`. Tool annotations unverified (14 of 20). Only `domain` is required on the endpoints read, and no SDKs exist (8 of 15). Total 67. 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. ## 7. Transparency & trust, 60 out of 100, up to 3.5 more on the total Made of editorial 45, provenance 75. Why it scored 60: Closed service under public terms last updated 19 March 2025 (15 of 30). The privacy policy, amended 30 June 2026, states retention as long as reasonably necessary with no periods, and no public DPA was found (12 of 30). Deprecations carry dates, such as Demographics 1.0 on 1 January 2025 and legacy REST endpoints on 6 October 2026 with a mapping table, but no written notice policy was found (12 of 20). The privacy policy says servers are in the United States, and no sub-processor list was found on the public pages (6 of 20). Total 45. 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) - Status page: not found (0 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: MCP tool definitions, tool count and annotations, which need a subscription key to list - unchecked: the V5 changelog entries at https://docs.similarweb.com/changelog/similarweb/api-v5, which load in the browser and didn't reach our reader - unchecked: https://trustcenter.similarweb.com/ answered with a bot check, so the DPA, sub-processor list and any disclosure policy there weren't read - unchecked: whether the legacy REST endpoints stopped answering on 6 October 2026 as the migration guide says - No dollar price per data credit or for the API-only package was found on public pages - The privacy and security page links bugcrowd.com in its markup with no programme named, so no bug bounty is recorded - Rank tracking endpoints appear in the V4 reference only, and no V5 replacement was found in the V5 index ## Weaknesses - API and MCP access need a Business, Enterprise or API-only plan bought through sales. The FAQ says there's no API test without a subscription - No public status page found. similarweb.statuspage.io redirects to a Statuspage login - No public OpenAPI file or official SDK found. The FAQ answers the SDK question by saying any HTTP client works - No backlink endpoint in the V5 or V4 API reference, although the website lists a Backlink Analytics product - The SLA page is dated January 2016 and its linked PDF returns 404 ## 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 the key in the `api-key` header. The capabilities endpoint documents `?api_key=` in the URL, which puts the secret in logs - Stay under 10 requests a second. A 429 can also mean the monthly credit allowance is spent, so call `/capabilities` (free) before retrying - Pass domains in lower case without `www.` or a path. The docs list 401 as data not found for a malformed domain - Request only the metrics, countries and months needed. Credits multiply across domains, metrics, countries and periods, and daily granularity costs about 30 times monthly - Website keywords accept monthly granularity for the last three months only, and `position` isn't returned for worldwide ## 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.