Keywords Everywhere API + MCP

# Fix list: Keywords Everywhere API + MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/keywords-everywhere, the October 2026 research run, assessed 9 October 2026. Grade D, 47.2 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 Keywords Everywhere 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. Reliability, 42 out of 100, up to 11.6 more on the total

Why it scored 42: Graded on the hosted lines for the REST API and the MCP server. status.keywordseverywhere.com is the vendor's own page with a 90-day timeline by day. It has one component, the website, and none for the API or the MCP server (12 of 20). Seven days between 12 July and 9 October 2026 are marked Outage (1 and 11 August, 1, 8, 12, 16 and 17 September) and the page gives 92.22 per cent for the period. It has no incident notes or durations, so the outages can't be sized (5 of 30). The MCP docs state 120 tool calls a minute per account. No limit was found for the REST API (10 of 15). The MCP docs say to wait a minute and retry after a Too many requests error. No Retry-After header and no 429 entry appear in the REST status tables. Every call is a read (5 of 15). No SLA was found, and the terms disclaim continuous or uninterrupted access (0). The API is V1 and neither it nor the MCP server carries a beta label (10). Total 42.

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, 20 out of 100, up to 10 more on the total

Why it scored 20: No x402, MPP or L402 (0). Four annual plans are priced in public with their credit amounts, and the docs give a credit cost for every endpoint, so a keyword lookup works out at $0.00084 on Bronze and $0.00018 on Platinum (20). The API key is free, but data calls need a paid plan and no trial or free credits were found. Only balance, country and currency lookups cost nothing (0). A person enters an email address in a browser form and follows an emailed link to get the key, and buys a plan through Paddle (0). Total 20.

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, 47 out of 100, up to 9.3 more on the total

Why it scored 47: One API key per account, sent as a Bearer token and reset through an emailed link. It has no scopes and is shared by every seat on the plan and by the browser extension. The MCP server adds OAuth 2.1 with dynamic client registration, PKCE and 3-hour access tokens, and its docs say the key is stored encrypted with AES-256-GCM. Links on the vendor's own site carry the key as an `apiKey` query parameter to the subscription pages. The API docs show only the header (18 of 30). Every endpoint and tool is read-only and nothing in the account can be changed. A key can spend the whole credit balance, and no cap per key was found (14 of 20). Responses carry third-party anchor text, URLs and keywords, and no prompt-injection guidance was found (3 of 15). Each response returns `credits_consumed` and the account has a stats page. No per-call log for the customer is documented (5 of 15). A security overview of July 2026 describes access control, patching and 72-hour breach notice, and states that the vendor holds no SOC 2 or ISO 27001 certification. No security.txt, disclosure policy or bug bounty was found (7 of 20). Total 47.

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, 48 out of 100, up to 8.5 more on the total

Why it scored 48: No OpenAPI file or other machine-readable contract was found for the REST API. The MCP server's input schemas weren't read, because its robots.txt closes the endpoint (5 of 25). keywordseverywhere.com/llms.txt answered 404. The API reference is a docsify site whose pages are plain Markdown files, which a model can read directly (5 of 10). Each page states the endpoint's purpose and credit cost in a line or two, and the API overview says the service is not a rank tracker and that competition is an advertiser metric (11 of 20). Parameter tables give type, examples, options (`gkp` or `cli`), a range of 1 to 10,000 for `num` and a 100-keyword ceiling. Required status isn't stated (9 of 15). Every endpoint has request samples in eight languages, a sample response, a status code table and sample 401 and 402 bodies. There is no sample for 400 (13 of 15). Paths are versioned under `/v1` and the MCP registry entry carries a version. The only changelog is for the browser extension (5 of 15). Total 48.

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, 54 out of 100, up to 7.5 more on the total

Why it scored 54: The MCP server has 14 tools, which is 15 on the MCP line. The size of the definitions wasn't read (15 of 25). `num` caps the rows returned by keyword and backlink lists and `get_keyword_data` takes up to 100 keywords a call. No offset, cursor, filter or field selection was found, so a second page of results can't be requested (9 of 20). Errors are JSON with a `message` such as `402 Insufficient Credits` and, on some endpoints, a `description`. 400 is documented only as invalid request data (11 of 20). Every endpoint and tool is a read, so a retry changes nothing in the account, though a repeated call spends credits again. The vendor says every tool is read-only. Tool annotations weren't read (12 of 20). Most parameters are optional and volume is global when `country` is omitted. No SDK was found. The vendor publishes an n8n node and code samples in eight languages (7 of 15). Total 54.

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. Maintenance & community, 63 out of 100, up to 3.2 more on the total

Why it scored 63: The official MCP registry dates version 2.0.0 of `com.keywordseverywhere/keywords-everywhere` at 10 September 2026, 29 days before the check, and the security overview and DPA were updated in July 2026 (30). The only dated changelog is the browser extension's, with three versions in the last 90 days (15 July, 2 and 16 September). One dated entry was found for the API or the MCP server in that time (8 of 20). A product news page lists known issues with fix dates, and support is by email. No forum or public issue tracker was found (8 of 15). The server is in the official registry under the `com.keywordseverywhere` namespace (15). No SDK or public repository was found, and the vendor's n8n node on npm has been at 0.1.5 since 27 April 2025 (2 of 10). Total 63.

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, 68 out of 100, up to 2.8 more on the total

Made of editorial 49, provenance 87.

Why it scored 68: Closed service. The Terms of Service date from 30 May 2023, are adapted from the WordPress terms, and don't mention the API, reuse or resale of the data, or the legal entity. The vendor's n8n node is MIT (8 of 30). A privacy policy of 15 August 2025, a DPA of July 2026 that applies to every customer without signature, and a security overview give retention figures of about 30 days for web server logs and no more than 90 days for backups, and the MCP docs say the server keeps request counters and short-lived logs only. The privacy policy describes its scope as the browser add-on and says only an email address is required, while the DPA lists names, keyword queries and usage data (19 of 30). No deprecation policy was found. The terms allow termination of access at any time without notice, and the only dated API notice is the banner of 7 June 2025 (3 of 20). Six sub-processors are named with purpose and location, with 30 days' notice of changes, and the DPA says data is stored mainly in the EU, also in the United States, and accessed from India (19 of 20). Total 49.

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 4 of the 7 things a reader expects (7.4 of 10)
- Privacy policy: read, states 7 of the 8 things a reader expects (9.3 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 MCP server's tool definitions, input schemas and annotations. robots.txt on mcp.keywordseverywhere.com disallows every path but /docs, so the endpoint and its OAuth discovery documents were not requested. The tool list and the read-only claim are the vendor's
- unchecked: ten of the 15 API reference pages (countries, currencies, related and PASF keywords, URL keywords, URL traffic and three backlink pages). Five endpoint pages, the README and the MCP page were read, and the others are assumed to follow the same layout
- unchecked: top-up credit prices and any Enterprise price, which sit behind the account page or an email address
- Whether the status page's Outage days reflect the API and the MCP server. It has one component, the website, and gives no durations
- Whether a REST rate limit exists. None was found in the pages read
- Whether a failed or empty call is charged credits. The docs say cost is per result returned and don't address errors
- The Terms of Service say nothing on automated access, storing or reselling the data. They also don't name the contracting entity, which the DPA and privacy policy give as Axeman Technology Solutions LLP
- The main site's MCP page says Windsurf can't use the remote HTTP transport, while the MCP host's docs list Windsurf among clients that can
- The lead was right about the interfaces and the docs link. It gave the vendor as Keywords Everywhere. The operator is Axeman Technology Solutions LLP of Mumbai

## Weaknesses

- No free credits or trial. Data calls need an annual plan, from $84 for 100,000 credits that expire after a year
- No OpenAPI file, llms.txt or official SDK was found. The reference is 15 Markdown pages behind a docsify viewer
- No rate limit is documented for the REST API. The only published limit is 120 MCP tool calls a minute per account
- The status page tracks only the website and marks seven of the last 90 days as Outage, with no incident notes
- One unscoped key per account, shared by up to 20 seats and by the browser extension, with no spending cap per key found
- The Terms of Service date from 30 May 2023 and say nothing about the API, data reuse, rate limits or deprecation

## 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: Bearer <key>` to `https://api.keywordseverywhere.com/v1`. The same key works on the MCP server
- Call `GET /v1/account/credits` (free) before a large pull. A short balance returns 402 with `402 Insufficient Credits`
- Set `num` on domain, URL and backlink lookups. It accepts 1 to 10,000 and every returned row is charged 1, 2 or 5 credits
- Batch up to 100 keywords in one `get_keyword_data` call and set `country`. Without it the figures are global
- Keep MCP use under 120 tool calls a minute per account, and wait a minute after a Too many requests error

## 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.