# Fix list: SE Ranking API + MCP From Anchor Terminal's listing at https://www.anchorterminal.com/tools/se-ranking, the October 2026 research run, assessed 8 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 SE Ranking 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. Security & auth, 21 out of 100, up to 13.8 more on the total Why it scored 21: API keys are created and named in the API dashboard, several to an account, and the MCP server signs in by OAuth 2.1 with dynamic client registration. Keys have no scopes, and the terms mention rotation only where available (22). The key is also accepted as an `apikey` query parameter on every API, and the OpenAPI file documents only that method (minus 10, leaving 12). The MCP docs say restricted or read-only keys aren't available yet and that a key has the same access as the account. No approval step was found for Project API deletes (3). Responses carry third-party anchor text, page titles and AI answers, and no prompt-injection guidance was found (0). The API dashboard shows credit usage and the terms say SE Ranking keeps API logs. No per-call log for the customer is documented (4). No security page, SOC 2 or ISO 27001 statement or bug bounty was found, and /.well-known/security.txt answered 403. The privacy statement says security measures are in place without naming them (2). Total 21. 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. Reliability, 51 out of 100, up to 9.8 more on the total Why it scored 51: Graded on the hosted lines for the REST APIs and the MCP server. A status page titled SE Ranking Online Status answers at status.seranking.com, run on Pulsetic. It isn't linked from the pages we read and its components are drawn by script, so we could confirm the page but not its components (12 of 20). Its incident history was unreadable for the same reason (5). Limits are published as 10 requests a second for the Data API, 5 for the Project API and 1 for trial accounts, counted per key over a rolling second (15). The docs describe 429 and recommend exponential backoff with jitter. No Retry-After header and no idempotency key for Project API writes were found, and repeated overruns block the Project API for 10 minutes (10). Section 2.1 of the API terms says there is no service level agreement unless a separate written agreement states one (0). The Data API, Project API and MCP server carry no preview label. The SE Visible API is marked Beta (9). Total 51. 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. ## 3. Payments & pricing, 40 out of 100, up to 7.5 more on the total Why it scored 40: No x402, MPP or L402 (0). The docs publish a credit cost for every Data API endpoint and dollar prices for credits, from $50 for 250,000 pay-as-you-go credits to $179 per million on the smallest annual plan (20). The pricing page states a 14-day trial with 100,000 credits, API and MCP access and no card (20). A person signs up in a browser and confirms an email address before a key is issued (0). Total 40. 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. ## 4. Schema & documentation, 58 out of 100, up to 6.8 more on the total Why it scored 58: An OpenAPI 3.0.0 file for the Data API (64 paths, 86 operations) is in the vendor's GitHub organisation. Every response in it is a 200 with no schema, it has no file for the Project, Local Marketing or SE Visible APIs, and the docs pages we read link a Postman collection instead. MCP input schemas weren't read (14 of 25). seranking.com/llms.txt and /api/llms.txt return 404 and no Markdown twins were found (0). Each endpoint page states its purpose, cost and every parameter, and the pricing FAQ says when to use the Data API and when the Project API (14). Parameter tables give type, required status, default and ranges, and the spec carries 56 enums. Filters are bracketed query parameters (11). Every endpoint has a curl request and a JSON response sample and each API has an error table. The tables disagree, with `Insufficient funds` given as 403 on one page and 400 on another (11). Paths are versioned under `/v1`. The What's New page lists API releases by year without dates in its HTML, and the registry dates each MCP version (8). Total 58. 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. Agent ergonomics, 58 out of 100, up to 6.8 more on the total Why it scored 58: The MCP page says the server has 180+ tools, and no toolset, read-only subset or tool filter is documented, which is 5 on the MCP line. Data API calls take `cols` and `limit` to size a response, so we scored between the two (10). `limit` on 24 operations and `offset` on 13 in the spec, with `order_field` and range filters on keyword and domain reports. `limit` above 1,000 is capped without an error (17). Errors are JSON with a code, message and description, and the tables list the common causes. Status codes for the same error differ between pages (14). Data API reads are safe to repeat and 4xx and 5xx responses cost no credits. No idempotency key was found for Project API writes and MCP annotations weren't read (10). Few required parameters and stated defaults. The vendor's API page says there are no first-party SDKs (7). Total 58. 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. ## 6. Transparency & trust, 71 out of 100, up to 2.5 more on the total Made of editorial 59, provenance 83. Why it scored 71: Closed service with API Terms of Service dated 3 March 2026 that cover commercial use, credits and credentials. Sections 1.3 and 2.6 say credentials are specific to each API and section 1.15 ties the Project API to Business or Enterprise plans, while the docs say one key works everywhere on every plan. The skills and OpenAPI repositories are MIT (14 of 30). The privacy statement of 25 June 2026 gives retention periods by purpose and says personal data isn't used to train general AI models. Retention of API logs is left to that statement, no DPA is on the legal page, and the API terms link a privacy URL that differs from the live one (19). Section 13 of the API terms promises up to 30 days' notice of breaking changes where practicable and reserves removal of deprecated functionality at any time (9). A processors page of 25 June 2026 names each processor with purpose and country, Hetzner in Germany and Amazon Web Services in Luxembourg for hosting, and promises two weeks' notice of new ones (17). Total 59. 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 3 clauses that cost points (3.1 of 10) - security.txt: could not be fetched (0 of 10) ## 7. Maintenance & community, 79 out of 100, up to 1.8 more on the total Why it scored 79: The official MCP registry dates version 2.5.1 of `com.seranking/mcp` at 28 September 2026, 10 days before the check (30). Six versions were published in the last 90 days, on 17 July, 18 August and 8, 15, 24 and 28 September (20). A What's New page, a support address for the API, a demo booking form and public GitHub repositories with issues open to all. We found no developer forum (9). The server is in the official registry under the `com.seranking` namespace (15). The OpenAPI repository has a lint workflow and one commit on its main branch, from 8 April 2026, and the skills repository has CI and signed releases to version 2.10.4 (5). Total 79. 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: the status page's components and incident history. status.seranking.com is drawn by script and we did not pull its data feed, so reliability may be understated by up to 33 points or overstated by 12 - unchecked: the MCP server's tool definitions, input schemas, annotations and exact tool count, which need a signed-in account. The 180+ figure is the vendor's - unchecked: dates of What's New entries, which the page loads by script. Maintenance dates come from the MCP registry - unchecked: /.well-known/security.txt, which answered 403 - unchecked: whether a key can be deleted or rotated in the API dashboard, and whether the dashboard has a per-call log - unchecked: OAuth scopes of the MCP server. `https://api.seranking.com/.well-known/oauth-authorization-server` returned 404 - The pricing page showed our request prices in pounds. The dollar prices recorded are from the docs pages - The API terms say credentials are specific to each API and the Project API needs a Business or Enterprise plan. The docs say one key and every plan. We recorded the docs and noted the terms - The docs give the smallest standalone plan as 12 million credits a year in one place and 24 million in another, and the pricing page labels it 1M credits a year - The OpenAPI repository is in the vendor's GitHub organisation and is not linked from the docs pages we read. Its SERP paths (`/v1/serp/classic/*`) have no page in the docs sidebar - No security page or certification statement was found in the page sitemap, the legal index or the footer. If one exists elsewhere the security score is understated - The last few requests ran shortly after midnight on 9 October 2026. Dates are recorded as 2026-10-08 as the brief directs ## Weaknesses - No scoped or read-only keys. The MCP docs say a key has the same access as the account, including Project API deletes - The API key is accepted as an `apikey` query parameter, and the OpenAPI file and its README describe only that method - No security page, certification statement, bug bounty or readable security.txt was found, and the API terms say there is no SLA without a separate agreement - The MCP server advertises 180+ tools with no documented way to load a subset - The API terms let SE Ranking remove deprecated functionality at any time, with up to 30 days' notice only where practicable ## 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 as `Authorization: Token `, not `Bearer` and not `?apikey=`, so it stays out of URLs and logs - Call `GET /v1/account/subscription` (0 credits) and read `units_left` before a large pull. A short balance returns `Insufficient funds` - Set `limit` and `cols` on per-record endpoints. Backlink summaries cost 100 credits a target and keyword rows 10 credits each - Stay under 10 requests a second on the Data API and 5 on the Project API per key. Repeated overruns block the Project API for 10 minutes - Ask the owner before any Project API or `PROJECT_*` create, update or delete call. The key has no read-only mode and nothing confirms a delete ## 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.