mcp-scraper@0.38.2
Upgrade to mcp-scraper 0.98.0 or newer. Older releases include obsolete local execution code; see the packaged README for hosted-client migration.
MCP server for MCP Scraper web intelligence tools
AI Security Review
scanned 3mo ago · by lpm-firewall-aiSource inspection found a real but explicit AI-agent configuration capability, with no unconsented install-time execution or concrete malicious chain. Warn under the firewall policy for explicit-user-command agent config mutation.
Static reason
One or more suspicious static signals were detected.; previous stored version diff introduced dangerous source
Trigger
User runs `mcp-scraper-cli agent install claude --apply` with an API key.
Impact
Adds or replaces the mcp-scraper MCP server in Claude Code's user configuration.
Mechanism
CLI-driven Claude MCP remove/add registration
AI rationale
Source inspection found a real but explicit AI-agent configuration capability, with no unconsented install-time execution or concrete malicious chain. Warn under the firewall policy for explicit-user-command agent config mutation.
Evidence
package.jsondist/bin/mcp-scraper-cli.jsdist/bin/mcp-stdio-server.jsdist/index.cjsREADME.md
Network endpoints2
mcpscraper.devregistry.npmjs.org/mcp-scraper/latest
Decision evidence
public snapshotAI called this Suspicious at 91.0% confidence as Dangerous Capability with low false-positive risk.
Evidence for warning
- Explicit `agent install claude --apply` removes and re-adds a user-scope Claude MCP entry.
- The CLI invokes the external `claude` command via `spawn` only in that explicit apply path.
Evidence against
- `package.json` has no preinstall/install/postinstall lifecycle hook.
- Codex and Claude Desktop paths only print configuration.
- No eval, dynamic code loading, or credential harvesting/exfiltration found.
- Hosted API requests use configured key and package-aligned `mcpscraper.dev` endpoint.
Behavioral surface
ChildProcessCryptoEnvironmentVarsFilesystemNetworkShell
HighEntropyStringsObfuscatedUrlStrings
NoLicense
Source & flagged code
6 flaggeddist/server-5EX6XBIA.jsView file
27523patternName = generic_password
severity = medium
line = 27523
matchedText = url.pass...D]";
Medium
Secret Pattern
Package contains a possible secret pattern.
dist/server-5EX6XBIA.jsView on unpkg · L2752364computeIssues,
L65: isPrivateIpAddress,
L66: validatePublicHttpUrl
...
L295: ctaHeadingItalic: "real data.",
L296: ctaBody: "MCP Scraper gives your AI workflows the web intelligence they need \u2014 SERP data, People Also Ask harvests, page extraction, YouTube transcripts, and more. All via API...
L297: sections: [
...
L558: answer: `<strong>ChatGPT makes things up because its RLHF training consistently rewarded fluent, complete-sounding answers \u2014 and human raters often cannot tell in the moment w...
L559: source: "https://techcrunch.com/2026/05/05/openai-releases-gpt-5-5-instant-a-new-default-model-for-chatgpt/"
L560: }
...
L606: question: "what is the hallucination rate of Claude in 2026",
L607: answer: `<strong>Claude's hallucination rate in 2026 spans from 0% (Claude Opus 4.1
Low
Weak Crypto
Package source references weak cryptographic algorithms.
dist/server-5EX6XBIA.jsView on unpkg · L64dist/bin/mcp-stdio-server.cjsView file
Findings
5 High4 Medium7 Low
HighChild Processdist/bin/mcp-stdio-server.cjs
HighShell
HighSame File Env Network Executiondist/bin/mcp-scraper-cli.js
HighSandbox Evasion Gated Capabilitydist/bin/mcp-scraper-cli.js
HighPrevious Version Dangerous Deltadist/bin/mcp-stdio-server.cjs
MediumSecret Patterndist/server-5EX6XBIA.js
MediumNetwork
MediumEnvironment Vars
MediumStructural Risk Force Deep Review
LowScripts Present
LowWeak Cryptodist/server-5EX6XBIA.js
LowFilesystem
LowObfuscated
LowHigh Entropy Strings
LowUrl Strings
Affected versions and remediation
This report applies to mcp-scraper@0.38.2.
See all versions of mcp-scraper for other recorded verdicts.
- Review the evidence and your use of mcp-scraper@0.38.2 before allowing it. Restrict the permissions described in this report.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.