CrawlForge MCP Server
crawlforge-mcp-server
npm
v6.0.0
Published by mysleekdesigns — no publish provenance, so origin is unverified, but the source is public: the repository link below is self-declared yet readable, so you can inspect the code before adopting it.
27 web scraping, crawling, deep-research, and autonomous-extraction tools returning clean Markdown and structured JSON.
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 1.2 = 99. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −1.2 | Package runs install-time scripts MTC-SUP-010 | supply-chain |
2. Client adoption risk — 99 − 7 = 92. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −6 | capability blast radius (high) — client exposure if the model is manipulated |
| −1 | publisher verification (public source) — no provenance, but the source is public and inspectable |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Findings 5
high Dynamic code execution in server code (src/core/ActionExecutor.js)MTC-SRC-001
In the server's implementation (`src/core/ActionExecutor.js:1112`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: [ page.evaluate(new Function('...args', script), ...args), timeout ]); } finally { clear
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/core/ActionExecutor.js
medium Hardcoded egress to an external endpoint (src/core/LocalizationManager.js)MTC-SRC-003
In the server's implementation (`src/core/LocalizationManager.js:1079`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: const response = await fetch('http://httpbin.org/ip', { method: 'GET', headers: identityHeaders({ role:
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/core/LocalizationManager.js
medium Hardcoded egress to an external endpoint (src/core/StealthBrowserManager.js)MTC-SRC-003
In the server's implementation (`src/core/StealthBrowserManager.js:2672`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: onst sessionRes = await fetch('https://www.browserbase.com/v1/sessions', { method: 'POST', headers: {
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/core/StealthBrowserManager.js
medium Hardcoded egress to an external endpoint (src/monitoring/healthCheck.js)MTC-SRC-003
In the server's implementation (`src/monitoring/healthCheck.js:456`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: const response = await fetch('https://www.google.com', { method: 'HEAD', signal: controller.signal
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/monitoring/healthCheck.js
low Package runs install-time scripts (postinstall)MTC-SUP-010
"crawlforge-mcp-server" executes postinstall script(s) at install time. An install hook runs at install time; most are routine build/setup, but review what it does before trusting it.
Evidence: echo '
CrawlForge MCP Server installed!
Quick start: run "npx crawlforge init" to configure your API key, install skills, and register the MCP server with your
Fix: Review the scripts; install with --ignore-scripts where possible and vet what they do.
Location: package crawlforge-mcp-server
What this scan could not see
- No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
Versions 10
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v6.0.0 latest |
A 92/100 | 5 | 1.13.0 | 2026-09-07 |
v5.9.0 |
A 92/100 | 5 | 1.13.0 | 2026-09-06 |
v5.6.10 |
A 92/100 | 5 | 1.13.0 | 2026-09-05 |
v5.6.1 |
A 92/100 | 5 | 1.13.0 | 2026-09-04 |
v5.5.9 |
A 92/100 | 5 | 1.13.0 | 2026-08-31 |
Show 5 more versions ↓
v5.4.1 |
A 92/100 | 5 | 1.13.0 | 2026-08-30 |
v5.3.1 |
A 92/100 | 5 | 1.13.0 | 2026-08-29 |
v5.2.9 |
A 92/100 | 5 | 1.13.0 | 2026-08-27 |
v5.1.0 |
A 92/100 | 5 | 1.13.0 | 2026-08-25 |
v5.0.5 |
A 92/100 | 5 | 1.12.1 | 2026-08-24 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan crawlforge-mcp-server --onlineMore in Web, Search & Scraping
Agent IP: MCP server with patents search tools
MCP server for searching the Agent Almanac — the public catalog of 9,000+ Model Context Protocol servers. Find, install, and discover MCP servers from inside Claude Desktop, Cursor, Continue, Zed, or any MCP-aware agent.
Search agents & MCP servers by capability, with daily-observed pricing, liveness and market data.
Verified merchants accepting agentic payments on Lightning/L402/BOLT12/USDT — search, verify, pay.
Airframe MCP Client - Connect agents to Airframe's product intelligence
Amazon product search demand over time, with growth for any keyword. Free key at trendsmcp.ai