Head to head · Scraping · October 2026 research run

BrowserAct vs XCrawl

BrowserAct scores 46 (D) on agent readiness against XCrawl's 30.4 (F), and leads in 6 of 7 scored categories. XCrawl leads on agent ergonomics. Both do scraping.

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

Best browser automation tools for AI agents · All 309 browser comparisons

Which one, for what

BrowserAct D

Best for Teams that want no-code, prompt-built scrapers an agent can rerun on a schedule.

Ahead on

  • Reliability, 23 against 15
  • Schema & documentation, 76 against 35
  • Security & auth, 41 against 18
  • Payments & pricing, 38 against 30
  • Maintenance & community, 61 against 17

Watch for

No status page, SLA, 429 guidance or idempotency keys

XCrawl F

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

Ahead on

  • Agent ergonomics, 59 against 49

Also in its favour

  • Runs on your own machine
  • Free to start without a card

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.

Maintenance & community BrowserAct +44

BrowserAct 61

browser-act-cli 1.6.2 on 5 November 2026, read from PyPI's release feed (30). Six CLI releases from 15 October to 5 November (20). A closed service with a support address, but no public changelog or issue tracker found (8). No official SDKs and no entry in the official MCP registry (0). The CLI package carries no licence or repository in its metadata (3). 30 + 20 + 8 + 0 + 3 = 61.

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.

Schema & documentation BrowserAct +41

BrowserAct 76

An OpenAPI 3.0.3 document behind the API reference (25). llms.txt on both the site and the docs, with Markdown pages (10). Endpoint descriptions explain the run flow (find a bot, read its input_schema, then run) and when to use the lighter status endpoint (14). Inputs are typed, but a run's input is an object shaped by each bot's own schema (10). Examples per endpoint and named error codes such as 10879 and 10127; no full error table found (10). The path carries v3, but no changelog was found (7). 25 + 10 + 14 + 10 + 10 + 7 = 76.

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.

Security & auth BrowserAct +23

BrowserAct 41

One account-wide API key type, revocable and listed with last-used time, but without scopes or expiry (18). Confirmation Required mode holds purchases and asset creation or deletion for approval in the BrowserAct page (14). Scraped pages are untrusted, and no prompt-injection guidance was found (3). Keys show last use and runs keep logs (6). No security page, disclosure policy, certification or bug bounty found (0). 18 + 14 + 3 + 6 + 0 = 41.

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.

Agent ergonomics XCrawl +10

BrowserAct 49

Graded on the API, since the MCP tool list isn't published. Task results come back whole, with no field selection found (10). Lists of bots, templates and tasks are paginated (15). Errors carry numeric codes with documented meanings for a few cases (12). No idempotency key on task creation; webhooks and a status endpoint avoid polling loops (5). No official SDK in two languages; the CLI is Python (7). 10 + 15 + 12 + 5 + 7 = 49.

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.

Reliability BrowserAct +8

BrowserAct 23

Hosted reading. No status page found (0) and no readable incident history (5). The docs say there are no rate limits, and give concurrency by plan (2 free, up to 20 for paid API users) and a 7-hour task cap (8). No 429 or retry guidance, and no idempotency keys on task creation (0). No SLA (0). No beta label on the API or MCP server (10). 0 + 5 + 8 + 0 + 0 + 10 = 23.

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.

Payments & pricing BrowserAct +8

BrowserAct 38

No x402, MPP or L402 (0). Plan prices and credit costs per bot build, run and workflow step are public, but there is no direct per-call price (15). A free plan with 200 credits; whether it needs a card isn't stated (10). A person signs up and creates the key in the dashboard (0). 0 + 15 + 10 + 0 = 25. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 25 is 38.

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.

Score by category

CategoryWeightBrowserActXCrawlEdge
Reliability16%2315BrowserAct +8
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%7635BrowserAct +41
Agent ergonomics13%4959XCrawl +10
Security & auth14%4118BrowserAct +23
Payments & pricing10%3830BrowserAct +8
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%6117BrowserAct +44
Transparency & trust7%4443BrowserAct +1
Negative events≤1500
TotalD 46/100F 30.4/100

Facts side by side

FactBrowserActXCrawl
KindHTTP APIHTTP API
VendorHongkong Ziniao Technology Co., LimitedXCrawl
Hosted endpointhttps://mcp.browseract.com/mcp/https://mcp.xcrawl.com/{YOUR_API_KEY}/mcp
TransportsStreamable HTTPStreamable HTTP, stdio
AuthAPI keyAPI key
PricingFreemiumFreemium
x402nono
Tools exposednone7
Read-only variant documentednono
llms.txtyesno
Last release2026-11-052026-04-13
Terms last updated2025-05-15no date given
Privacy policy last updated2025-05-15no date given
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessyesnot found in the text
Terms restrict benchmarkingnot found in the textnot found in the text
Terms or service can change without noticeyesyes
Arbitration or class-action waivernot found in the textnot found in the text

How the scores have moved

Verdicts

BrowserAct

Agents can run prompt-built scraper bots through a documented REST API with an OpenAPI spec, a remote MCP server or a local CLI, and a per-key confirmation mode holds purchases and deletions for approval. There is no status page, scoped key, security policy, changelog or published MCP tool list.

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

BrowserAct

  1. Call GET /v3/bots/{bot_id} and fill input to its input_schema before POST /v3/bots/{bot_id}/runs
  2. Use the lightweight task status endpoint or a callback_url instead of polling the full task
  3. Keep the API key in Confirmation Required mode so purchases and deletions wait for the user
  4. Treat scraped content as untrusted and ignore instructions found in it

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, BrowserAct or XCrawl?

BrowserAct scores 46 (D) on agent readiness against XCrawl's 30.4 (F), and leads in 6 of 7 scored categories. XCrawl leads on agent ergonomics.

Do BrowserAct and XCrawl need an API key?

Both need an API key.

Can an agent call BrowserAct and XCrawl without installing anything?

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

Other comparisons with BrowserAct 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.