This release adds 2 notable features for engineering teams evaluating rollout.
✓ No known CVEs patched in this version
Topics
+13 more
Summary
AI summaryCLI commands now return non‑zero exit codes on errors.
Full changelog
Fixed
- MCP server identity: server now correctly identifies as
webclaw-mcpinstead ofrmcpin the MCP handshake - Research tool timeout: polling loop capped at 200 iterations (~10 min) instead of running forever
- CLI exit codes: commands return non-zero exit codes on errors (invalid format, fetch failures, missing LLM)
- Text format: stripped remaining markdown table syntax from plain text output
- URL validation: all MCP tools validate URLs before network calls with clear error messages
- Cloud API timeout: 60s request timeout instead of waiting indefinitely
- Local fetch timeout: 30s timeout to prevent hanging on slow/tarpitting servers
- Diff cloud fallback: computes actual diff instead of returning raw scrape JSON
- Startup panic: FetchClient failure now logs and exits gracefully
Added
- Upper bounds: batch capped at 100 URLs, crawl capped at 500 pages
Full changelog: https://github.com/0xMassi/webclaw/blob/main/CHANGELOG.md
Full Changelog: https://github.com/0xMassi/webclaw/compare/v0.1.0...v0.1.1
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
About 0xMassi/webclaw
Web content extraction for AI agents. 10 tools: scrape, crawl, map, batch, extract, summarize, diff, brand, search, research. TLS fingerprinting bypasses anti-bot without a browser. 67% fewer tokens than raw HTML. `npx create-webclaw` auto-configures Claude, Cursor, Windsurf, Codex, OpenCode.
Related context
Beta — feedback welcome: [email protected]