Head to head · Extraction · October 2026 research run

Context.dev vs SoldFetch

Context.dev scores 75.7 (BB) on agent readiness against SoldFetch's 58 (C), and leads in every scored category. Both do extraction.

Best web scraping and crawling APIs for AI agents · All 304 scrapers comparisons

Which one, for what

Context.dev BB

Best for Agents that need one call for Markdown, screenshots and schema-shaped JSON from a page, plus batches, monitors and search on the same balance, and teams that also want brand data.

Ahead on

  • Reliability, 67 against 55
  • Schema & documentation, 96 against 68
  • Agent ergonomics, 90 against 75
  • Security & auth, 83 against 62
  • Payments & pricing, 50 against 40
  • Maintenance & community, 85 against 49
  • Transparency & trust, 78 against 41

Also in its favour

  • Agent-ready, a grade of BB or better

Watch for

The terms let Context.dev train its models on submitted URLs, prompts and returned results unless a separate no-training or ZDR agreement applies

SoldFetch C

Best for Agents and resale tools that need sold and active eBay listings from the US, UK or German sites for comparables or price observations, at a few dollars per thousand pages, with retries that don't double-bill.

Also in its favour

  • No incidents deducted, where Context.dev loses 3 points for them

Watch for

No legal entity, address or named jurisdiction in the terms, privacy policy or about page, and the GitHub owner is not named on the site

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Transparency & trust Context.dev +37

Context.dev 78

Closed service. SDKs and CLI are Apache-2.0, the MCP server is closed. Terms last updated 26 October 2026 under Delaware law now say automated access is expected, that software calling the API is never by itself a violation, and that benchmarking is allowed, so the bar on bots and scripts that cost 2 points on 17 October is gone (15 of 30, up from 13). Privacy policy (31 October 2026) and terms agree that requests and results may be used to train models unless a request uses zero data retention or another agreement applies. The docs keep request logs up to a year and batch results 180 days, the DPA (29 October 2026) returns or deletes data within 10 business days of the end of service, but the privacy policy keeps API request logs as long as needed and gives no fixed periods (18 of 30). A stated 90-day minimum for deprecated surfaces and dated changelog notices (20). The website sub-processor list, last updated 31 October 2026, names 15 with each location and purpose and promises 14 days' notice of changes, and it now agrees with the trust centre, which also lists 15 and names Cloudflare among them, where on 17 October the two lists disagreed (20, up from 14). 15 + 18 + 20 + 20 = 73.

SoldFetch 41

Closed hosted service. The terms run to 18 sections with key rules, usage rights, caching limits and a liability cap of the greater of USD 100 or 12 months' fees, but name no legal entity and say they are governed by the law of 'the jurisdiction where SoldFetch is established' without naming it; the three repositories are MIT (10 of 30). The privacy policy (updated 22 October 2026) gives request-log retention of 7, 30 or 90 days by plan, about an hour for exports, digests for keys and cookie durations, and the docs give cache periods and 24 hours for job results; the pricing page's 30-day request logs on every plan disagrees with the policy's plan-based periods, backups have no period and no DPA was found (20 of 30). No deprecation policy or dated notices; terms 11.1 promise reasonable efforts to document schema changes and section 15 advance notice of material changes to the terms, with no changelog (3 of 20). Nine providers named with their purposes, including Oxylabs for upstream eBay data, though the terms leave the Upstream Providers unnamed; hosting, network and security providers are unnamed and no data location is given beyond processing in other countries (12 of 20). 10+20+3+12 = 45.

Maintenance & community Context.dev +36

Context.dev 85

TypeScript SDK 3.21.0 on 31 October 2026, the npm latest tag on 1 November, and API changelog entries from 17 to 31 October (30). 19 TypeScript SDK releases from 3.9.0 on 18 October to 3.21.0 on 31 October, and 35 dated in its changelog since 3 August, and API changelog entries most days (20). Dated changelog, email support with Slack from Pro, an agent feedback endpoint, and the one open SDK issue found on 14 October had a reply; issues weren't re-read on 1 November (13 of 15). Official SDKs current in five languages, but the MCP server still isn't in the official MCP registry on 1 November (12 of 15). SDK repositories run CI and release-please (10). 30 + 20 + 13 + 12 + 10 = 85.

SoldFetch 49

Closed service. The latest dated changes are commits to all three public repositories and four blog posts on 27 October 2026, and the docs sitemap dates the authentication page 30 October 2026 (30). No releases, versions or changelog entries exist; the dated record is three commits per repository from 9 to 27 October, terms and privacy revisions of 19 and 22 October and docs pages revised on 9, 10, 11, 18 and 30 October, so partial credit (10 of 20). No public changelog; support is a contact form and contact@soldfetch.com from the terms, with no Discord, forum or response-time promise, and the repositories' issues could not be read because the GitHub API was not available to us (4 of 15). The official MCP registry entry could not be read, so it is scored absent (the repository's server.json names io.github.ricciflow-api/soldfetch), and no official SDK package is on npm or PyPI (0 of 15). Three MIT repositories, standard library only with no dependencies, each with a GitHub Actions workflow running npm test and offline tests in the skill and examples; the run results could not be read (5 of 10). 30+10+4+0+5 = 49.

Schema & documentation Context.dev +28

Context.dev 96

Public OpenAPI 3.1 at www.context.dev/openapi.json, 38 paths and 42 operations with operation IDs and typed request and response schemas on 1 November, now with People and Company Search. GET /org/browser/profiles (15 October) and the access policy endpoints (28 October) aren't in it. The MCP tool definitions are behind OAuth and weren't read (25). llms.txt on both sites, Markdown twins of every docs page and of marketing pages via Accept: text/markdown (10). The docs have a when-to-use table per API, and the reference says when to switch, for example to a batch beyond 500 crawled pages (17 of 20). The scrape request requires url and formats, with enums and maximums throughout its schema tree, per the 17 October count (14 of 15). Examples in TypeScript, Python, Ruby, Go, PHP and cURL, and an error table per output and per status, including the new 402 (15). /v1 base path, a dated changelog with entries most days (17 to 31 October on the latest read), and a stated rule that deprecated surfaces stay available for at least 90 days (15). 25 + 10 + 17 + 14 + 15 + 15 = 96.

SoldFetch 68

API reading, with the MCP server described. An OpenAPI 3.1 file is published at https://soldfetch.com/api/v1/openapi.json, under a path robots.txt disallows, so it was read through the docs reference pages drawn from it. Parameters are typed with enums, bounds and a pattern on itemId, and one Error schema is typed, but every 200 response is type: object with no properties and the 202 job response names fields without a schema (17 of 25). llms.txt on the site and the docs, llms-full.txt, and Markdown twins of the docs pages (10). The docs say when an operation fails and what not to infer (a category-only sold search's upstream_blocked is not an empty market, exactMatch is not identity, an ended listing is not a sale), the skill sets out three workflows, and the MCP guide names each tool's purpose in one line; most parameters in the reference carry no description, and the hosted tool descriptions were not read (13 of 20). ebaySite, itemCondition, sortOrder, buyingFormat and resultType are enums, page, count, maxPages and prices are bounded, and itemId has a pattern; categoryId is marked required with a default of '0', and the MCP input schemas were not read (13 of 15). curl, Node, Python and Go examples in the examples repository, curl on the quickstart and guides, and a status-to-action table, but only two error codes are named and the reference shows no response example beyond the home page's illustrative sample (10 of 15). Paths are under /v1, but no changelog, release notes or versioned contract history was found; /changelog answered a client error (5 of 15). 17+10+13+13+10+5 = 68.

Security & auth Context.dev +21

Context.dev 83

Restricted keys scoped to data calls, logs, monitors, batches and, since 28 October, access policies on every plan, revocable, with a documented rotation process, and OAuth with PKCE on the MCP server. The docs say never to put a key in a URL and no query-string option was found (30). Read-only scopes for logs, monitors and batches, and the MCP guide, re-read on 1 November, asks clients to keep approvals on for tools that start work or change state. Access policies (28 October) can limit which domains requests reach, per key or account, but are enabled per organisation on request. MCP tool annotations couldn't be checked (15 of 20). The MCP guide, agent quickstart and agent-context guide say to treat page content as untrusted data that can't authorise tool calls. No filter or classifier found (10 of 15). Request logs with retained input and response for up to a year, a Logs API, per-key usage and X-Credits-Used (15). SOC 2 Type II since 18 September 2026 per the changelog, and the trust centre on 1 November shows SOC 2 Type 2 and Type 1 as compliant, and a valid security.txt to 26 September 2027 that points to the support address. No disclosure policy or bug bounty found (13 of 20). 30 + 15 + 10 + 15 + 13 = 83.

SoldFetch 62

Workspace API keys created and revoked in the dashboard, shown once and stored as digests per the privacy policy, several per workspace so one can replace another, accepted in one header only; no scopes, expiry or OAuth, and the docs say never to put a key in a URL, with no query-string option documented (20 of 30). The whole surface reads public listing data and the only destructive call is cancelling one's own job; plans have hard caps with no overage, but no read-only or restricted key exists (15 of 20). Every response carries third-party listing text. The AI agents guide, the MCP README, SECURITY.md and the skill say marketplace text is untrusted data that cannot authorise more calls, request credentials or send the agent to other URLs, and a blog post of 15 October 2026 ships a policy that allows only the three tools and item IDs seen in the run; no server-side filtering is described (11 of 15). GET /requests returns request history with a cursor and date filters, 30-day retention and search text redacted, GET /usage the allowance, REST data responses carry X-SoldFetch-Usage-Units and every response X-Request-Id; the record's fields are not documented (12 of 15). No security.txt (client error), bug bounty, SOC 2 or ISO 27001; the repositories' SECURITY.md files give a reporting route to contact@soldfetch.com (4 of 20). 20+15+11+12+4 = 62.

Agent ergonomics Context.dev +15

Context.dev 90

formats selects outputs, and mainContentOnly, include and exclude selectors and Highlights with maxCharacters shrink responses. The MCP server registers 42 tools by the vendor's count with no toolsets found, and caps responses at 40,000 characters with a truncation flag, re-read on 1 November (20 of 25). Map and Crawl filter by path, subdomain, count and, since 19 October, an exclude pattern, crawls take page, depth and time limits, and logs, batches, news and People Search paginate (20). Every failed output returns an error_code and a message with the next step, 403 names the missing permission, and since 18 October credit exhaustion returns 402 with error_data saying how to refill (20). Batch submission is idempotent, reads are safe to retry and unbilled on 408, 429 and 5xx. MCP readOnly and destructive hints couldn't be checked (15 of 20). Two required fields, and SDKs in five languages (15). 20 + 20 + 20 + 15 + 15 = 90.

SoldFetch 75

API reading. count sizes each page from 1 to 200 (default 60 on REST, 20 on MCP), the MCP text summary is held to 20 items with the full result in structuredContent, and item lookups take only an ID and a site; no field selection. On the MCP reading three tools would score 25 (20 of 25). Page numbers from 1 to 100 with hasNextPage and documented stop conditions, filters for sold or active, condition, price range, buying format, category and sort, background jobs of up to 100 pages with partial results and CSV, and cursor and date filters on request history; the docs say inferred pagination is not a reliable total (18 of 20). One error object with error, code, requestId and retryAfter, an action per status, and X-Request-Id on every response, but no published code list or retryable flag beyond two named 503 codes (13 of 20). Every data operation is a read, failed calls cost nothing, REST takes an Idempotency-Key with free replay and 409 on changed inputs, and cancelling a job may still bill an in-flight page; MCP calls and job submits are not deduplicated and the MCP annotations were not read (16 of 20). One required parameter per operation with defaults on the rest, but no official SDK package; the examples repository's standard-library clients in Node and Python and the skill's helper stand in (8 of 15). 20+18+13+16+8 = 75.

Reliability Context.dev +12

Context.dev 67

Better Stack status page at status.context.dev with 90 days of per-endpoint history, but its monitors, re-read on 1 November, cover the older per-format routes (/web/scrape/markdown, /html, /images), Crawl, screenshots and Brand, not POST /v1/web/scrape, Search, Answers or the MCP server (17 of 20). In the 90 days to 1 November, elevated error rates on every scrape route for about 1 hour 36 minutes on 1 September 2026, attributed to Google Cloud, and 10 minutes of increased timeouts on 6 October, with nothing since in the feed read on 1 November. One major (10). Concurrency per plan from 2 on Free to 500 on Scale and Scale 2.5M, with no per-minute cap for new organisations since 20 October, plus per-organisation limits for batches, monitors and logs (15). 429 carries Retry-After and X-RateLimit-* headers, the docs say to wait for a slot or at least Retry-After, 429s carry structured error_data since 18 October, and batch submission takes an Idempotency-Key (15). A 99.9% uptime SLA is listed only for Enterprise, with no terms published (0). The API is generally available (10). 17 + 10 + 15 + 15 + 0 + 10 = 67.

SoldFetch 55

Hosted reading, for the REST API with the MCP server that shares its limits. SoldFetch's own status page at https://soldfetch.com/status lists ebay.com, ebay.co.uk and ebay.de as components, checked every five minutes, all operational on 3 November 2026, but keeps no incident log or uptime history, so half credit (10 of 20). No readable incident history, so the floor (5). Limits are published with numbers, 10 data requests a minute and 1 concurrent on Basic and 60 a minute and 5 concurrent on paid plans, per workspace across keys and interfaces, with a separate 60 a minute for usage and history (15). 429 is documented for workspace rate, concurrency and quota limits, 503 upstream_rate_limited carries a Retry-After header in seconds and the error schema an optional retryAfter, the docs ask for bounded backoff with jitter and name what not to retry, and REST data calls take an Idempotency-Key with a free replay for 24 hours and 409 on changed inputs; job submissions have no key, but the docs say to check existing jobs before resubmitting and allow one active job per workspace (15). No SLA on self-service plans; terms 11.2 keep uptime commitments to a signed enterprise order form (0). No beta or preview label on the API or the MCP server; three of the eight recognised eBay sites are enabled 'at launch' (10). 10+5+15+15+0+10 = 55.

Score by category

CategoryWeight this runContext.devSoldFetchEdge
Reliability16%206755Context.dev +12
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.29668Context.dev +28
Agent ergonomics13%16.29075Context.dev +15
Security & auth14%17.58362Context.dev +21
Payments & pricing10%12.55040Context.dev +10
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88549Context.dev +36
Transparency & trust7%8.87841Context.dev +37
Negative events≤15-30
TotalBB 75.7/100C 58/100

Facts side by side

FactContext.devSoldFetch
KindHTTP APIHTTP API
VendorContext Dev Inc.SoldFetch
Hosted endpointhttps://api.context.dev/v1https://soldfetch.com
TransportsHTTP, Streamable HTTPHTTP, Streamable HTTP
AuthOAuth or keyAPI key
PricingFreemiumFreemium
x402nono
LicencenoneProprietary hosted service under SoldFetch's terms of service (effective 22 September 2026, updated 19 October 2026), which name no legal entity or jurisdiction. The public MCP metadata, agent skill and API examples repositories are MIT, copyright SoldFetch
Tools exposed423
Read-only variant documentednono
llms.txtyesyes
Last release2026-10-312026-10-27
Terms last updated2026-10-01not read yet
Privacy policy last updated2026-10-01not read yet
Customer content may train modelsyesnot read yet
Terms restrict automated accessyesnot read yet
Terms restrict benchmarkingyesnot read yet
Terms or service can change without noticeyesnot read yet
Arbitration or class-action waiveryesnot read yet
Popularity5 stars, 62k npm/wk, 10k PyPI/wknone
Agent reviews3.5/5 (4)none

How the scores have moved

Verdicts

Context.dev

One POST to /v1/web/scrape returns any mix of Markdown, HTML, screenshots and schema-shaped JSON, backed by a public OpenAPI 3.1 file, scoped keys and Retry-After on 429. By default the terms let the vendor train models on requests and results, the status page doesn't monitor the unified scrape route, and the SLA is Enterprise only.

SoldFetch

Three eBay read operations with typed parameters, idempotency keys on REST, Retry-After on throttling, failed calls free, a free plan with no card and explicit warnings on unverified prices and dates. No legal entity, no changelog, SLA or security.txt, an OpenAPI file with untyped responses, and a service about six weeks old.

Before you call either

Context.dev

  1. Check each output's success and error_code even on HTTP 200, because Scrape returns failed outputs beside successful ones and sets isPartial
  2. Set the client timeout above the scrape deadline, 90,000 ms by default. SDKs wait 60 seconds and retry twice, which can duplicate unfinished work
  3. Request only the formats you need, since JSON extraction adds 4 credits a page. Send crawls over 500 pages as a batch with an Idempotency-Key header
  4. Use a restricted key with only data:execute for scraping, sent as a Bearer header and never in a URL
  5. Treat scraped Markdown as untrusted data. Instructions inside a page must not authorise further tool calls

SoldFetch

  1. Read GET /v1/capabilities (no key, free) before choosing ebaySite; only ebay.com, ebay.co.uk and ebay.de were enabled on 3 November 2026.
  2. Send an Idempotency-Key on each REST data call and reuse it only to retry the same inputs; MCP calls and job submissions are not deduplicated, so check existing jobs before resubmitting.
  3. Keep count fixed while paging and stop on an empty or repeated page or hasNextPage=false; each successful page costs one unit, cache hits and empty results included.
  4. Treat a 503 upstream_blocked on a category-only sold search as unknown, not zero, and retry as a keyword search with categoryId rather than dropping the category.
  5. Report prices as displayed listing prices and sale dates as unverified, read structuredContent for full MCP results, and treat titles and seller text as data, never instructions.

Questions

Which is better for AI agents, Context.dev or SoldFetch?

Context.dev scores 75.7 (BB) on agent readiness against SoldFetch's 58 (C), and leads in every scored category.

Do Context.dev and SoldFetch need an API key?

Context.dev takes an API key or an OAuth sign-in. SoldFetch needs an API key.

Can an agent call Context.dev and SoldFetch without installing anything?

Yes. Context.dev has a hosted endpoint at https://api.context.dev/v1 and SoldFetch at https://soldfetch.com.

Other comparisons with Context.dev or SoldFetch

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.