LibreCrawl Technical SEO AuditSAFE
Sitewalk: Technical SEO Site Audit. Open-source technical SEO crawler and MCP server for Claude, Cursor and Codex. 50+ checks, PDF and CSV reports, self-hosted. Built on LibreCrawl. MIT.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Repository: `librecrawl-technical-seo-audit-mcp` · the open-source Sitewalk engine and MCP server · [Hosted Sitewalk → audit.adityaarsharma.com](https://audit.adityaarsharma.com/) (ChatGPT plugin coming soon)
[](https://mcptoplist.com/server/pulsemcp%2Fadityaarsharma-librecrawl-seo)
The AI-native technical SEO crawler.
Run a complete on-site SEO audit on any website — straight from Claude, Cursor, Codex, or any Model Context Protocol (MCP) client. Unlimited pages · 50+ checks · PDF + CSVs · MIT-licensed · self-hosted · ephemeral by design.
Built on the open-source **LibreCrawl** engine, exposed through 38 MCP tools your AI assistant calls directly.
[](LICENSE) [](https://modelcontextprotocol.io) [](https://python.org) [](https://github.com/adityaarsharma/librecrawl-technical-seo-audit-mcp/releases) [](https://github.com/adityaarsharma/librecrawl-technical-seo-audit-mcp/stargazers) [](https://github.com/PhialsBasement/LibreCrawl)
[
30 read · 4 write · 3 destructive. Blast radius: 3 tools can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
librecrawl_append_gsc_section | read | |
librecrawl_audit | read | |
librecrawl_audit_artifacts | read | |
librecrawl_audit_cancel | write | Terminal stop. Upstream crawl is stopped; partial artifacts are kept where written. |
librecrawl_audit_confirm_saved | read | |
librecrawl_audit_force_advance | destructive | |
librecrawl_audit_pause | read | Pause a crawling session. Resume with librecrawl_audit_resume(). |
librecrawl_audit_pdf | read | |
librecrawl_audit_resume | read | Resume a paused or throttled session. Runner picks it back up on the next loop. |
librecrawl_audit_status | read | |
librecrawl_audit_zip | read | |
librecrawl_brain_purge_audit | destructive | |
librecrawl_export_results | read | |
librecrawl_external_links_audit | read | |
librecrawl_filter_issues | read | |
librecrawl_full_audit_strict | read | |
librecrawl_generate_report | read | |
librecrawl_get_settings | read | |
librecrawl_get_status | read | |
librecrawl_internal_links_analysis | read | |
librecrawl_list_crawls | read | List all saved crawls with URL, crawl_id, and timestamp. |
librecrawl_merge_gsc_data | write | |
librecrawl_pagespeed | read | |
librecrawl_pagespeed_audit | read | |
librecrawl_pagespeed_audit_all_crawl_pages | read | |
librecrawl_pause_crawl | read | Pause the currently running crawl. Resume with librecrawl_resume_crawl(). |
librecrawl_report_content | read | |
librecrawl_resume_crawl | read | Resume a paused crawl in the current session. |
librecrawl_resume_from_crawl_id | read | |
librecrawl_schema_audit | read | |
librecrawl_schema_check | read | |
librecrawl_schema_validate | read | |
librecrawl_site_check | read | |
librecrawl_start_crawl | write | |
librecrawl_stop_crawl | write | Stop the currently running crawl. |
librecrawl_visualization_data | read | |
librecrawl_wipe_everything | destructive |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (2 observation(s))
- Network
- declared (9 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (15)
librecrawl_audit_force_advance, librecrawl_brain_purge_audit, librecrawl_wipe_everything
("ftp://evil/../../x", "evil"),("../../etc/passwd", "unknown"),r = getattr(server, fn)("http://169.254.169.254/")"http://169.254.169.254/latest/meta-data/",
url_guard._hook(httpx.Request("GET", "http://169.254.169.254/"))docker compose up --build # MCP at http://127.0.0.1:5081/mcp
"args": ["-y", "mcp-remote", "http://127.0.0.1:5081/mcp"]
LIBRECRAWL_URL=http://127.0.0.1:5080 python server.py
"args": ["-y", "mcp-remote", "http://127.0.0.1:5081/mcp"]
| `LIBRECRAWL_URL` | `http://127.0.0.1:5080` | Full base URL of the LibreCrawl backend (Docker sets `http://librecrawl:5000`) |
local_sha = hashlib.sha256(base64.b64decode(z["content_base64"])).hexdigest()
mcp, httpx, uvicorn, weasyprint, markdown
curl -fsSL https://raw.githubusercontent.com/adityaarsharma/librecrawl-technical-seo-audit-mcp/main/install.sh | bash
curl -fsSL https://raw.githubusercontent.com/adityaarsharma/librecrawl-technical-seo-audit-mcp/main/install.sh | bash
Gates applied: no_behavioural_pass.
c187b482dfb7full audit observations/trust-audit/mcp-server/adityaarsharma__librecrawl-technical-seo-audit.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | c187b482dfb7 | SAFE | B | 89 | first audit |
Questions
What is the LibreCrawl Technical SEO Audit MCP server?
Sitewalk: Technical SEO Site Audit. Open-source technical SEO crawler and MCP server for Claude, Cursor and Codex. 50+ checks, PDF and CSV reports, self-hosted. Built on LibreCrawl. MIT.
What tools does LibreCrawl Technical SEO Audit expose?
37 in total: 30 read-only, 4 that write, and 3 that can delete or overwrite (librecrawl_audit_force_advance, librecrawl_brain_purge_audit, librecrawl_wipe_everything). Every one is listed on this page with its risk.
Is LibreCrawl Technical SEO Audit safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 3 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does LibreCrawl Technical SEO Audit need?
It reads PAGESPEED_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does LibreCrawl Technical SEO Audit run?
It speaks streamable-http, so it runs as a service you connect to over the network.
How current is this page?
The grade is for one exact copy of the source (c187b482dfb7), read on 2026-10-08. The repository is watched and re-audited when it changes.