Search ScrapeBLOCK
A unified web extraction and stateful automation engine for AI. Replaces heavy testing frameworks with token-optimized browser control, deep research, and HITL.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
CortexScout is the Deep Research & Web Extraction module within the Cortex-Works ecosystem.
Designed for agent workloads that require token-efficient web retrieval, reliable anti-bot handling, and optional Human-in-the-Loop (HITL) fallback.
Overview
CortexScout provides a single, self-hostable Rust binary that exposes search, extraction, and stateful browser automation capabilities over MCP (stdio) and an optional HTTP server. Output formats are structured and optimized for downstream LLM use.
It is built to handle the practical failure modes of web retrieval (rate limits, bot challenges, JavaScript-heavy pages) through progressive fallbacks: native retrieval → Chromium CDP rendering → Stateful E2E Testing → HITL workflows.
Tools (Capability Roster)
a3c3065317c0OBSERVED · 2026-10-08Exposed tools (7)
7 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
browser_close | read | Close the persistent headless browser session started by scout_browser_automate. Call when done with all automation steps to free memory and release the browser process. |
crawl_website | read | Legacy alias for |
fetch_then_extract | read | Legacy alias/variant of structured extraction. Prefer |
human_auth_session | read | Legacy auth-focused alias of HITL flow. Equivalent to |
non_robot_search | read | Unified HITL escalation tool. Use |
scrape_batch | read | Legacy alias for |
scrape_url | read | Unified web content tool. Supports single-page fetch, batch fetch, and site crawl via |
Trust audit
BLOCKgrade F · trust 55/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | WARN |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (10 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (17)
"Ubuntu/Debian: `sudo apt-get update && sudo apt-get install -y chromium-browser`"
"Fedora: `sudo dnf install -y chromium`".to_string(),
"Arch: `sudo pacman -S chromium`".to_string(),
"Ubuntu/Debian (recommended): `sudo apt-get update && sudo apt-get install -y zenity`"
"Alternative: `sudo apt-get install -y yad`".to_string(),
"/usr/local/bin/chromium",
std::env::var("NATIVE_HTTP_URL").unwrap_or_else(|_| "http://127.0.0.1:5000".to_string());std::env::var("LEGACY_HTTP_URL").unwrap_or_else(|_| "http://127.0.0.1:5001".to_string());let json_url = format!("http://127.0.0.1:{}/json/version", debugging_port);let json_url = format!("http://127.0.0.1:{}/json/version", debugging_port);let list_url = format!("http://127.0.0.1:{}/json/list", debugging_port);pub const CORTEX_SCOUT_ICON: &str = "data:image/svg+xml;base64,PHN2ZyB3aWR0aD0iNTEyIiBoZWlnaHQ9IjUxMiIgdmlld0JveD0iMCAwIDUxMiA1MTIiIGZpbGw9Im5vbmUiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyI+CiAgI
system use found in code, not declared in the description
- Re-tested the exact `web_fetch` MCP request from the stuck-user report against `https://llvm.org/docs/CodeGenerator.html` with `output_format=clean_json`, `strict_relevance=true`, `extract_relevant_
proof/Screenshot-nowsecure.png
proof/airbnb_evidence.json
proof/ticketmaster_evidence.json
Gates applied: no_behavioural_pass.
a3c3065317c0full audit observations/trust-audit/mcp-server/devshero__search-scrape.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 | a3c3065317c0 | BLOCK | F | 55 | first audit |
Questions
What is the Search Scrape MCP server?
A unified web extraction and stateful automation engine for AI. Replaces heavy testing frameworks with token-optimized browser control, deep research, and HITL.
What tools does Search Scrape expose?
7 in total: 7 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Search Scrape safe to connect to an agent?
No — not without reading the findings first. The audit graded it F (55/100) and found 5 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What credentials does Search Scrape need?
No credential environment variables were found in its source, so it appears to need none.
How current is this page?
The grade is for one exact copy of the source (a3c3065317c0), read on 2026-10-08. The repository is watched and re-audited when it changes.