Head to head · Extraction · October 2026 research run

SoldFetch vs XCrawl

SoldFetch scores 45.5 (E) on agent readiness against XCrawl's 30.4 (F), and leads in 6 of 7 scored categories. Both do extraction.

Best web scraping and crawling APIs for AI agents · All 601 scrapers comparisons

Which one, for what

SoldFetch E

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.

Ahead on

  • Reliability, 55 against 15
  • Schema & documentation, 68 against 35
  • Agent ergonomics, 75 against 59
  • Security & auth, 62 against 18
  • Payments & pricing, 60 against 30
  • Maintenance & community, 49 against 17

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

XCrawl F

Best for A general scrape, crawl, map and SERP API for agents, with 35 site-specific data endpoints.

Also in its favour

  • Runs on your own machine
  • No incidents deducted, where SoldFetch loses 15 points for them

Watch for

Xcrawl LLC is named with no state, registration number or address, and the terms name no governing law

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.

Security & auth SoldFetch +44

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.

XCrawl 18

A plain bearer API key from the dashboard with no scopes, and the MCP guide says to reissue an invalid key there (20). The recommended hosted MCP setup puts the key in the URL path, so less 10, read the way the checklist reads a key in a query string (10 of 30). The API only reads third-party pages and has no destructive account actions, but there is no read-only or least-privilege key (5 of 20). No prompt-injection guidance in the docs or the skills (0 of 15). Each response reports credits used, and xcrawl_key_status gives the balance, with no request log found (3 of 15). No security.txt, disclosure policy or bug bounty. The ISO 27001 badge on the home page links to no certificate or security page (0 of 20). Total 18.

Reliability SoldFetch +40

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.

XCrawl 15

No status page found on xcrawl.com or docs.xcrawl.com (0 of 20) and no readable incident history (5 of 30). No rate limits with numbers. The pricing page says only that Scale plans get higher rate limits (0 of 15). No 429 or overload guidance in the docs. The Python SDK retries 500, 502, 503 and 504 with backoff, but not 429 (0 of 15). The terms mention a Service Level Agreement "if applicable", and none is published (0 of 10). The API is sold publicly with no beta label (10). Total 15.

Schema & documentation SoldFetch +33

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.

XCrawl 35

No OpenAPI or other machine-readable spec found, and the MCP package is closed source, so its tool schemas couldn't be read (0 of 25). llms.txt returns 404. The docs have "Copy page" buttons, and the xcrawl-skills repository has Markdown skill files for agents (5 of 10). Each API reference page states what the endpoint does, with no guidance on when not to use it (8 of 20). Parameter tables give types, required flags, defaults and enums for formats, device and wait_until. cookies and headers are free maps (11 of 15). Request and response examples on every reference page, but no error responses or codes documented outside the MCP troubleshooting table (6 of 15). Versioned /v1 paths and no changelog (5 of 15). Total 35.

Maintenance & community SoldFetch +32

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.

XCrawl 17

The newest dated releases are the Python SDK 1.1.2 on PyPI and the last xcrawl-sdk commits, both 13 April 2026, 221 days ago (0 of 30). Nothing dated in the 90 days from 22 August 2026 (0 of 20). We couldn't read GitHub issues. There is no public changelog, and support is by email, Telegram, WhatsApp and Microsoft Teams, with a 24-hour reply promised in the footer (5 of 15). Official Python and Node.js SDKs, unchanged for seven months (10 of 15). The SDK repository has 3 commits, no tests and no CI. Dependencies are current (2 of 10). Total 17.

Payments & pricing SoldFetch +30

SoldFetch 60

No x402, MPP or L402 on the pricing page, terms, llms.txt or docs, and no third-party machine payment route was found; the RapidAPI alias does not take RapidAPI authentication (0). Per-unit pricing is public without a login, 1 unit per successful search page or item lookup, $9 for 2,000, $29 for 10,000 and $79 for 50,000 a month, with what is and isn't charged stated (20). Basic gives 100 units once and the terms say no payment method is required (20). A person signs in through the browser and creates a key in the dashboard; no keyless API route or programmatic key creation, and the anonymous playground is a web page for people (0). 0+20+20+0 = 40. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 40 is 60.

XCrawl 30

No x402, MPP or L402 (0). The pricing page's plan table and credit table did not appear in the served page, and the docs give credit costs only in examples (1 for a plain scrape, 2 for a search), so pricing is scored absent (0 of 30, unchecked). 1,000 free credits on signup with no card (30). A person signs up in a browser at dash.xcrawl.com to get a key (0). Total 30.

Agent ergonomics SoldFetch +16

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.

XCrawl 59

7 MCP tools per the Claude Code guide, compact by name and description, though the definitions themselves couldn't be read (22 of 25). Output formats, only_main_content, a search limit of 1 to 100, and crawl limit, depth and include or exclude regex keep responses sized (16 of 20). The SDKs raise errors with a code, status and request_id, but the docs list no error codes or recovery steps (5 of 20). Async jobs return IDs for polling and webhooks, with no idempotency keys or MCP annotations found (3 of 20). Only url or query is required, and Python and Node.js SDKs exist, but skip_tls_verification defaults to true (13 of 15). Total 59.

Score by category

CategoryWeightSoldFetchXCrawlEdge
Reliability16%5515SoldFetch +40
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%6835SoldFetch +33
Agent ergonomics13%7559SoldFetch +16
Security & auth14%6218SoldFetch +44
Payments & pricing10%6030SoldFetch +30
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%4917SoldFetch +32
Transparency & trust7%4143XCrawl +2
Negative events≤15-150
TotalE 45.5/100F 30.4/100

Facts side by side

FactSoldFetchXCrawl
KindHTTP APIHTTP API
VendorSoldFetchXCrawl
Hosted endpointhttps://soldfetch.comhttps://mcp.xcrawl.com/{YOUR_API_KEY}/mcp
TransportsHTTP, Streamable HTTPStreamable HTTP, stdio
AuthAPI keyAPI key
PricingFreemiumFreemium
x402nono
LicenceProprietary 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 SoldFetchnone
Tools exposed37
Read-only variant documentednono
llms.txtyesno
Last release2026-10-272026-04-13
Terms last updatednot read yetno date given
Privacy policy last updatednot read yetno date given
Customer content may train modelsnot read yetnot found in the text
Terms restrict automated accessnot read yetnot found in the text
Terms restrict benchmarkingnot read yetnot found in the text
Terms or service can change without noticenot read yetyes
Arbitration or class-action waivernot read yetnot found in the text

How the scores have moved

Verdicts

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.

XCrawl

A scrape, search, map and crawl API with 7 MCP tools, MIT Python and Node.js SDKs and 1,000 free credits without a card. Xcrawl LLC gives no address or registration. There is no OpenAPI spec, status page, rate limit, error reference or changelog, plan prices did not render for us, and the hosted MCP key travels in the URL.

Before you call either

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.

XCrawl

  1. Use the npx xcrawl-mcp setup with XCRAWL_API_KEY in the environment rather than the hosted URL, which puts the key in the path
  2. Set skip_tls_verification to false when the page's certificate matters, because scrape and crawl default it to true
  3. Set crawler.limit and max_depth on every crawl, since the defaults are 100 pages and depth 3
  4. Call xcrawl_key_status before a large crawl, because the docs give no credit table to estimate the cost
  5. Treat scraped Markdown and JSON as untrusted page content, since the docs give no prompt-injection guidance

Questions

Which is better for AI agents, SoldFetch or XCrawl?

SoldFetch scores 45.5 (E) on agent readiness against XCrawl's 30.4 (F), and leads in 6 of 7 scored categories.

Do SoldFetch and XCrawl need an API key?

Both need an API key.

Can an agent call SoldFetch and XCrawl without installing anything?

Yes. SoldFetch has a hosted endpoint at https://soldfetch.com and XCrawl at https://mcp.xcrawl.com/{YOUR_API_KEY}/mcp.

Other comparisons with SoldFetch or XCrawl

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.