Nexscope vs ScrapingAnt

Nexscope 65

Read as a closed service with a public documentation repository. The repository synced the released 1688 procurement contracts on 9 November 2026 and committed again on 10 November (30). No releases or changelog. The dated record is the registry's four versions on 14 and 16 October, repository commits on 8, 9, 20 and 29 October and 2, 9 and 10 November, and source notes dating WooCommerce (29 October) and design search (2 November) additions. SoldFetch earned 10 for dated commits without releases (10 of 20). No public changelog. Support is service@nexscope.ai, WhatsApp and a booked call, untested. The repository's one merged pull request came from the organisation itself, and GitHub's API refused us, so issues weren't read (5 of 15). The official MCP registry lists io.github.nexscope/ecommerce, active, latest 1.0.3 of 16 October 2026, read first-hand (15). A CI workflow runs offline catalogue validation and unit tests on standard-library clients with no dependencies. The run results weren't read (5 of 10). 30+10+5+15+5 = 65.

ScrapingAnt 5

No changelog or dated API change found. The newest dated release of any vendor package is the GitHub Action v1.0.0, tagged 3 April 2026 (222 days), and the newest SDK is Python 2.1.0, tagged 16 July 2024 (0). No releases in the last 90 days (0). No public changelog. Support by email (3 of 15). The JavaScript client was last tagged v0.2.1 on 6 May 2022, so the SDKs aren't current, and no registry page shows ScrapingAnt's own MCP server (0). The Python client has a code-check workflow, but neither SDK has moved in over two years (2 of 10). 0 + 0 + 3 + 0 + 2 = 5.

Nexscope 44

Read on the MCP server, with the REST API where a line covers it. The MCP map lists 382 tools and says the category manifests 'narrow metadata for your integration; the MCP connection still advertises the full catalog'. That is more than 30 tools with no toolsets, dynamic loading or read-only subset found (5). Search tools page by page (about 20 results), with filters such as marketplace, category node, sort and device per tool, but no general pagination model or field selection, and output size depends on each tool (12 of 20). By default business errors answer HTTP 200 with an outer code. The X-Nexscope-Http-Status: semantic header maps them to HTTP statuses, the OpenAPI file names codes such as DATA_IMAGE_DOWNLOAD_FAILED and CAPABILITY_BACKEND_UNAVAILABLE in field text, and MCP errors aren't documented. SandBase earned 16 with typed bridge errors (11 of 20). Data calls only read. No idempotency keys and no readOnlyHint or destructiveHint documented. Async jobs return a taskId with a poll tool and a rule not to resubmit, and 1688 order, payment-link, receipt and cancel calls need an explicit JSON true confirmation (8 of 20). Few required parameters with defaults on most. No official SDK package, only standard-library clients in the repository for JavaScript and Python, which SoldFetch earned 8 for (8 of 15). 5+12+11+8+8 = 44.

ScrapingAnt 72

3 compact MCP tools (25). Markdown and text endpoints, AI extraction, wait-for-selector and a JSON extended response, but no output-size limit on the MCP tools (12 of 20). The errors page lists 7 statuses with exact detail messages, separates ScrapingAnt's status from the target's (Ant-page-status-code), and says for each whether to retry and what to fix (20, as scrapingdog). Requests are reads of third-party pages and failures aren't billed, but there are no idempotency keys or tool annotations (5 of 20). Only url is required, though browser defaults to true at 10 credits. Python and JavaScript clients exist but are stale (10 of 15). 25 + 12 + 20 + 5 + 10 = 72.

Nexscope 41

The MCP server takes OAuth 2.1 with PKCE and one scope, mcp:tools, per the tool pages, or a Bearer nk- API key. Keys are created by a person under API Access, shown once, and can be expired, disabled or deleted, with no scopes or rotation found. The OAuth metadata on api.nexscope.ai wasn't read. No query-string key option was found. Manifold earned 22 with OAuth and hashed keys whose storage it documents (20 of 30). Most tools read. Writes exist (1688 procurement on the user's own buyer account, Amazon Ads entity operations through an owned connection, paid generation jobs), and the 1688 calls need an explicit JSON true per action after a preview, with the guide saying to get the user's approval first. Credits cap spend. No read-only key or tool allowlist (12 of 20). Tools return third-party listings, reviews, social posts and web pages, and no prompt-injection guidance was found. Manifold, the closest marketing-data MCP, took 0 (0). The Account credits and Account usage APIs, costToken in data responses and credits charged on task results give per-call visibility. No key-level audit was found (9 of 15). security.txt answered a client error. No disclosure policy, bug bounty or certification found (0 of 20). 20+12+0+9+0 = 41.

ScrapingAnt 20

One account API key with no scopes. A new docs page explains how to regenerate it from the profile page, after which the old key answers 403 and an email confirms the change, so it is a plain revocable key (20). API Basics still tells you to send x-api-key as a query parameter, a documented option, so less 10 (10 of 30). The hosted MCP server now also accepts an OAuth sign-in bound to the active key. No read-only mode, and /v2/general can send POST, PUT and DELETE to target sites with no confirmation step; an IP allow-list can restrict where the key is used (5 of 20). No prompt-injection guidance found for the HTML, Markdown or text it returns (0 of 15). The Ant-credits-cost header and a subscription status endpoint show spend per call. No request log found (5 of 15). No security.txt, disclosure policy, bug bounty or certification found (0 of 20). 10 + 5 + 0 + 5 + 0 = 20.

Nexscope 64

A public OpenAPI 3.1 file at api.nexscope.ai/openapi.json, about 3.8 MB, linked from the quickstart. Visible request bodies are typed with required fields, patterns, enums and additionalProperties: false, but responses are open data objects and the components section, with the security scheme and the shared error response, wasn't reached. In the repository 166 of 252 request definitions are field descriptors rather than JSON Schema. The hosted tools/list wasn't read. SoldFetch took 17 with untyped responses and SandBase 22 with components unread (19 of 25). llms.txt on www.nexscope.ai and Markdown references for every API in the repository (10). MCP tool descriptions are one line ('Find Amazon products by keyword and marketplace. Results come back as structured JSON.'), with no when-not-to-use. The repository's references carry long trigger text ('trigger this skill whenever their need involves real-time Amazon search results'), not guidance on when to pick another tool (10 of 20). Tool pages list types, defaults, enums and length limits, but the Amazon Search page marks no argument required and omits the keyword its own examples pass, and many limits sit in prose (8 of 15). Every API has a request sample, a response fixture and cURL, JavaScript and Python clients, though most fixtures are labelled historical. Errors are an HTTP table, two named codes (11209, 12001) and a semantic error response whose schema wasn't read. MCP errors aren't documented (10 of 15). Path versioning under /v1, MCP v2 beside a legacy v1, and a dated OpenAPI version label, but no public changelog. SandBase earned 7 on the same pattern (7 of 15). 19+10+10+8+10+7 = 64.

ScrapingAnt 46

No OpenAPI or Swagger spec found. The MCP docs give a typed parameter table for the 3 tools (8 of 25). docs.scrapingant.com/llms.txt still returns 404 and no Markdown twins were found (0). MCP descriptions are one line each, such as Fetch a URL and return raw HTML content, with no when-to-use guidance (8 of 20). Few parameters, typed, with proxy_type as an enum of datacenter or residential (10 of 15). Request examples on every docs page, and an errors page that now gives each status code its exact detail text, cause and retry rule, plus a separate SDK errors page (15). Versioned paths (v1 and v2) and no changelog (5 of 15). 8 + 0 + 8 + 10 + 15 + 5 = 46.

Nexscope 41

The editorial half. The service is closed. The terms (8 October 2026) name ECOCREATE TECHNOLOGY PTE. LTD. under Singapore law with no registration number or address. The repository's MIT licence covers client code only, and the documentation and definitions stay copyright Nexscope. Scrapewise earned 15 for closed terms with MIT side code (15 of 30). The privacy policy (8 October 2026) says uploads are not used to train AI models and that connected selling-partner data is deleted or de-identified when no longer needed, but 'this policy does not specify a single deletion deadline for all data', and no DPA was found. SandBase took 12 with no retention periods (10 of 30). No deprecation policy or dated notices. The terms promise notice of material changes before they take effect where practicable, and the MCP map keeps a legacy v1 beside v2 (3 of 20). Analytics and advertising vendors are named (Google Analytics, Microsoft Clarity, Ahrefs, Google Ads, X, FirstPromoter), but hosting, AI processing and payment providers only by type, with no data locations. The repository's source notes say supplier references 'are presented as Nexscope', so the data suppliers go unnamed except LinkFox Agent for 1688 authorisation (5 of 20). 15+10+3+5 = 33. The provenance half is computed from the provenance block.

ScrapingAnt 56

Closed service with terms naming DATAANT SP. Z O.O., registered in Poland (KRS 0000848755). The SDKs are Apache 2.0 (15 of 30). The privacy policy, now last updated 21 October 2026, gives 12-month retention after an account closes, names processors and mentions DPAs with clients and transfers outside the EEA (Ukraine, the USA). It still doesn't cover the MCP server or the AI extractor, or say whether scraped content is stored (18 of 30). No deprecation policy or dated notices found (0). Processors and locations named, Sendgrid in Ireland, Paddle in the UK, Google Analytics and Amazon hosting in the USA (15 of 20). 15 + 18 + 0 + 15 = 48.

Nexscope 35

No x402, MPP or L402 on pricing, the quickstart, the MCP map, llms.txt or the visible OpenAPI paths. Credits come from a subscription or a Data top-up (0). Plans and credits per plan are public without a login ($29 for 30,000, $55 for 75,000, $129 for 150,000), and tool pages show credits per call, such as Amazon Search from 21 credits with a recent average of 30. Many tools on the MCP map list no cost and pricing is marked 'dynamic-credits'. Manifold earned 20 with a cost for every tool (15 of 20). A Free Trial of 1,000 credits for 3 days with 'No credit card required', API and MCP limits included. Creative API keys need a subscription (20). A person signs in through the browser to approve OAuth or create a key, and no keyless or programmatic route was found (0). 0+15+20+0 = 35.

ScrapingAnt 40

No x402, MPP or L402 (0). Credit costs per request type (1 to 125) and plan prices, Enthusiast $19 to Business Pro $599 and Custom from $699 a month, are public (20). 10,000 free credits a month, no card (20). A person signs up in a browser (0). 0 + 20 + 20 + 0 = 40.