Kagi Search API vs SERPHouse

Kagi Search API 64

Several named keys an account, each limited to chosen products and optionally to IP addresses or ranges, revoked by deleting. The v1 key travels only in the Authorization header. No expiry or OAuth (27). The API only reads. Per-key product limits and a spending cap in USD narrow what a leaked key can do (16). Search and Extract return third-party page text, and we found no prompt-injection guidance in the reference, the docs or the MCP README (2). The portal shows use count and last-used time per key and requests and cost per day per API, and every response carries a trace ID. No per-call log (7). security.txt with a contact, a bug bounty with a safe harbour policy, and an independent audit by Illumant cited on the security page, whose date we did not read. No SOC 2 or ISO 27001 statement found. security.txt re-read on 4 November (12). 27 + 16 + 2 + 7 + 12 = 64.

SERPHouse 11

One key per account, one account per user, no scopes or rotation found (10). The REST API documents api_token in the query string and the hosted MCP server takes the key only in its URL path, less 10 (0 of 30). Searches only read, with no read-only or restricted key (8 of 20). Results are third-party snippets and AI Overview text, with no prompt-injection guidance (0). An account tool shows plan and credit usage; no per-call log was found (3 of 15). No security.txt (404), disclosure policy, bug bounty or certification found (0 of 20). 0 + 8 + 0 + 3 + 0 = 11.

Kagi Search API 74

Closed service with clear API terms dated 22 September 2026. The MCP server is MIT and the OpenAPI file states Apache-2.0 (18). The privacy policy's API section agrees with the API terms. Queries are not stored against the account, load balancer and VM logs are kept 7 days and sampled Sentry errors 90 days. The Data Processing Addendum both documents cite is not yet published (23). v0 is marked deprecated with no end date, and the terms promise reasonable notice of breaking changes only where practicable (5). The privacy page names the payment processors and Sentry, the FAQ names GCP as the hosting provider and the docs name search sources, but there is no subprocessor list and no data locations (8). 18 + 23 + 5 + 8 = 54.

SERPHouse 50

Closed service under terms naming Patoliya Infotech LLP in India, and the MCP server is MIT (18 of 30). The terms give retention periods (JSON results up to 6 months, HTML up to 1 month, search history indefinitely) and say personal data sits on DigitalOcean in India, and they advise EEA users not to use the service. The privacy policy is generic and neither document carries a date (15 of 30). No deprecation policy, and the terms allow products to be discontinued without notice (0 of 20). DigitalOcean in India named for account data; no sub-processor list (6 of 20). 18 + 15 + 0 + 6 = 39.

Kagi Search API 20

No x402, MPP or L402 (0). $12 per 1,000 searches and $4 per 1,000 extracted pages, published without a login, unchanged on 4 November (20). No free tier or trial for the API. The quick start asks for a payment method, and the $5 credit of 21 May 2026 was a one-off for subscribers (0). A person signs up in a browser and creates the key in the portal (0). 0 + 20 + 0 + 0 = 20.

SERPHouse 40

No x402, MPP or L402 (0). Per-1,000 prices for SERP, autocomplete and top-100 requests published without login (20). Free trial of 4,000 credits for 7 days, 'No Credit Card Required' (20). A person signs up in a browser and confirms an email (0). 0 + 20 + 20 + 0 = 40.

Kagi Search API 41

The last dated API change is the Extract API fix in the changelog post of 21 August 2026, 75 days before this check. The posts of 10 September and 16 October carry no API item (20). That is the only dated API entry in the 90 days from 6 August (0). The MCP server's repository gained commits on 27 and 28 October 2026 (compact JSON results, readOnlyHint, per-page extraction errors) and a version bump to 1.1.0 with no tag, so no release is shown; PyPI didn't resolve for us. A public changelog that credits user reports, developers@kagi.com, a Discord #api forum and GitHub discussions. We could not read the issue list, since the GitHub API answered 403 (9). Four generated clients last synced on 26 May 2026, Python tagged only as 1.0.0rc3, TypeScript not on npm on 9 October, and kagimcp tagged last as v0.1.5 (8 April 2026). We did not look the server up in the MCP registry (8). The Python client has a generated CI workflow and the MCP server has a lock file but no CI workflow (4). 20 + 0 + 9 + 8 + 4 = 41.

SERPHouse 23

Read for a closed service, with its repositories read as code. No changelog or dated API change was found. The newest release is MCP server 1.1.0 on 6 July 2026, 123 days before 6 November, and the last commit in its repository was on 22 July (10). No release or dated change in the 90 days from 8 August; the about page's 2026 entry (Forums, Place Details and Scraper APIs) is undated (0). No changelog; support by email. Issues weren't read, since the GitHub API refused us for its rate limit (5 of 25). Not in the official MCP registry, though the repository's server.json names io.github.SERPHouse/serphouse-mcp. Node.js SDK last changed 24 June 2026, PHP SDK 10 May 2024, and no Python SDK repository was found under the SERPHouse organisation (5 of 15). The MCP repository has an npm publish workflow and no tests (3 of 10). 10 + 0 + 5 + 5 + 3 = 23.

Kagi Search API 75

limit caps results, extraction of page text is opt-in, snippet length follows an account setting, and an experimental Markdown response format exists. The MCP server has two tools (22). page 1 to 10, limit 1 to 1,024, lens and filters for domains, keywords, file type, dates and region (20). Errors return a namespaced code, a message, the field location and a trace ID, but no code catalogue is published and the linked error pages are not live (12). Both operations are read-only, so a retry is safe, though the docs do not say so and failed-call billing is stated only for extraction. The released MCP server sets no read-only annotations. A commit of 27 October adds readOnlyHint to its source with an untagged 1.1.0 version bump, not yet shown as released (10). Only query is required and defaults are stated. Generated clients exist for Python, TypeScript, Go and Rust, installable from GitHub. @kagi/api returned 404 on npm on 9 October (11). 22 + 20 + 12 + 10 + 11 = 75.

SERPHouse 64

23 MCP tools with no toolsets or filtering (15 of 25). num_result, max_pages, paging, device, location, language, date and video filters (16 of 20). Status codes are tabulated, but a 200 can also mean an error and the body carries only 'Please try again' (10 of 20). Searches only read and failed requests aren't charged, but the MCP tools carry no readOnlyHint or other annotations (10 of 20). serphouse_search needs only q and defaults to the US; most other tools need loc or loc_id. Official Node.js, PHP and Python SDKs are documented (13 of 15). 15 + 16 + 10 + 10 + 13 = 64.

Kagi Search API 71

Public OpenAPI 3.0 file at kagi.com/api/docs/_spec/openapi.yaml, linked as 'OpenAPI Spec' from the API overview page (25). No llms.txt on kagi.com or help.kagi.com, both 404. The docs' Markdown source is in a public GitHub repository, which is not the same as serving it to agents (0). Parameter descriptions say what each does and which option wins when lens, filters and query operators overlap, and the MCP tool says when to pick each workflow (14). Enums for workflow, format, time_relative and rule kinds, ranges on page, limit, timeout and extract.count, and one required field. Result props and meta are open objects (13). Three request examples with full responses and one 401 example. The error envelope is typed, but there is no list of error codes, and the file says its error documentation URLs return 404 for now (9). The path carries /v1 and v0 is documented as legacy. The changelog is product-wide, with API items on 21 May, 16 June and 21 August 2026 and none in the 10 September or 16 October posts (10). 25 + 0 + 14 + 13 + 9 + 10 = 71.

SERPHouse 66

No OpenAPI or similar contract for the REST API. The MCP server's tools carry typed Zod schemas, published in the source and a static server card (18 of 25). llms.txt at the site and the docs, and every docs page as Markdown (10). MCP tool descriptions say which tool to use for what, such as serphouse_google_web when device or num_result is needed, while the docs pages lead with marketing lines such as 'Unlock captivating Google video content' (12 of 20). Enums for device, SERP type, engine and video duration, defaults and 37 described parameters (11 of 15). A status code table and request examples per engine, with a generic error body (12 of 15). No changelog or API versioning; only the MCP server has tags (3 of 15). 18 + 10 + 12 + 11 + 12 + 3 = 66.