SearchAPI.io by SearchApi

# Fix list: SearchAPI.io

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/searchapi-io, the October 2026 research run, assessed 1 October 2026. Grade D, 51.4 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 SearchAPI.io: 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, 28 out of 100, up to 12.6 more on the total

Why it scored 28: API keys with a documented `api_key` query-string option, and OAuth with expiring, rotating tokens for the MCP. The official registry entry, published 29 January 2026, still puts the token in the MCP URL as `?token=`. 20 less 10 (10). Every action is a read, and there are no tool subsets (15). Results are third-party snippets and scraped AI answers, with no injection guidance (0). No per-call audit log found. The privacy policy says account logins are logged by IP (0). The trust centre at security.searchapi.io rendered nothing we could read. No certifications, bounty or security.txt found (3).

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. Payments & pricing, 30 out of 100, up to 8.8 more on the total

Why it scored 30: No x402, MPP or L402 (0). Monthly plans only, priced in public, from $40 for 10,000 searches to $5,000 for 5 million (10). 100 free requests with no card (20). A person has to sign up in a browser (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.

## 3. Agent ergonomics, 52 out of 100, up to 7.8 more on the total

Why it scored 52: The MCP exposes over 100 tools, one or more per engine, with no toolsets or filtering documented (5). `page`, `time_period`, location, country, language and safe search. Google's `num` has been fixed at 10 since September 2025 (18). Status codes are documented, but not how to recover from each (12). Searches are reads, and only HTTP 200 responses are billed, so retries are cheap. MCP annotations aren't visible (10). Two required parameters, `engine` and `q`. No official SDKs (7).

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.

## 4. Maintenance & community, 15 out of 100, up to 7.4 more on the total

Why it scored 15: No changelog (/changelog returns 404) and no dated API change we could find, so we can't date the last release (0). No releases to count (0). No public issue tracker or changelog to judge replies by (0). io.searchapi/mcp is in the official registry under SearchApi's own domain, version 1.0.0 from 29 January 2026 (15). No public packages or CI (0).

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.

## 5. Schema & documentation, 59 out of 100, up to 6.7 more on the total

Why it scored 59: OpenAPI 3.0 for the Google engine at /openapi/google.yaml with 25 typed parameters. We found no index of specs for the other engines, so 20 of 25. No llms.txt (404) and no Markdown docs for agents (0). The API reference explains each parameter, and the MCP tool definitions aren't public (10). Enums for device, country, language, safe search and time period (14). Examples and a Postman collection, and the spec documents 400, 401, 403, 429 and 500 (12). /api/v1 in the path and no changelog anywhere we looked (3).

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.

## 6. Transparency & trust, 62 out of 100, up to 3.3 more on the total

Made of editorial 48, provenance 76.

Why it scored 62: Closed service with published terms (15). Privacy policy dated 11 April 2026. Data sits in the US, cached results are purged on an unstated schedule, and zero retention is Enterprise only (15). Google's `num` phase-out is documented, and there's no deprecation policy (3). US data location stated, and the privacy policy links a subprocessor page (15).

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):

- Domain age: searchapi.io, registered 2017-12-13 (8 years) (11 of 15)
- Changelog: not found (0 of 10)
- security.txt: not found (0 of 10)

## 7. Reliability, 90 out of 100, up to 2 more on the total

Why it scored 90: Honeybadger status page at status.searchapi.io with API and landing-page components and monthly history (20). No incidents in August, September or October 2026, and July isn't shown. Two coarse uptime checks are all it tracks (30). The hourly cap is published, 20 per cent of the plan's monthly searches in any hour (15). The OpenAPI spec lists 429, but we found no `Retry-After` or backoff guidance (5). 99.9% SLA on every plan, per the pricing page (10). GA (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: incident history for July 2026, which the status page doesn't show
- unchecked: certifications and subprocessors, because security.searchapi.io needs JavaScript
- unchecked: support responsiveness, and whether any dated API changes are published somewhere other than /changelog
- Whether OpenAPI files exist for engines other than Google

## Weaknesses

- MCP exposes over 100 tools with no toolsets
- API key accepted as `api_key` in the query string, and the registry entry puts the MCP token in the URL
- No changelog, no llms.txt and no official SDKs
- No x402 and no per-call option. Every account starts with a browser signup
- Returns SERP snippets only, and no prompt-injection guidance for scraped AI answers

## 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`, not `api_key=` in the URL
- Connect the MCP through OAuth or the `X-MCP-Token` header, not the registry's `?token=` URL
- Call the REST API with `engine=` when context is tight. The MCP loads over 100 tool definitions
- Page Google results with `page`. `num` is fixed at 10
- Pace bursts. One hour can use at most 20 per cent of the plan's monthly searches

## What the review panel asked for

- Pay-per-call option
- Programmatic signup
- MCP toolsets
- llms.txt

## 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.