io.github.ZenRows/zenrows-mcp
io.github.ZenRows/zenrows-mcp · v2.19.0 · score 89/100 · checked 2026-11-22
Automated, read-only signal from public data, not an audit or an accusation. Maintainers can dispute any finding. How grading works
Zenrows MCP server: Fetch, Extract, Batch, and Browser Sessions for AI agents
Source: https://github.com/ZenRows/zenrows-mcp
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 62 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 1 tool(s) can execute commands or delete data (batch_delete). Require confirmation before the agent calls them. |
What was checked
- https://mcp.zenrows.com/mcp: answers without auth
- npm: @zenrows/mcp@2.19.0 (static checks only; code not executed)
Public tools: scrape, extract, prepare_domain, prepared_domain_status, batch_create, batch_status, batch_wait, batch_results, batch_content, batch_list, batch_cancel, batch_pause, batch_resume, batch_rerun, batch_delete, crawl_create, crawl_get, crawl_results, crawl_content, crawl_list, crawl_stop, crawl_wait, crawl_download, account_usage, browser_navigate, browser_close, browser_go_back, browser_go_forward, browser_reload, browser_click
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-github-zenrows-zenrows-mcp-df6d2405)