Webpeel MCP Server
webpeel
npm
v0.22.0
Published by webpeel — 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.
The web data platform for AI agents — fetch, search, crawl, extract, monitor, screenshot. 55+ domain extractors, 65-98% token savings, MCP server included. One API call.
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 | Hardcoded Google API key in server code MTC-SRC-008 | exfiltration |
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 14
high Shell/command execution in server code (dist/core/browser-pool.js)MTC-SRC-002
In the server's implementation (`dist/core/browser-pool.js:9`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: port { execSync } from 'child_process'; // Re-export closePool so fetcher.ts can barrel it from this module. export { cl
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 dist/core/browser-pool.js
high Shell/command execution in server code (dist/core/peel-tls.js)MTC-SRC-002
In the server's implementation (`dist/core/peel-tls.js:11`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: import { spawn } from 'child_process'; import { randomBytes } from 'crypto'; import { platform, arch } from 'os'; impor
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 dist/core/peel-tls.js
high Shell/command execution in server code (dist/core/youtube.js)MTC-SRC-002
In the server's implementation (`dist/core/youtube.js:8`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: { execFile } from 'node:child_process'; import * as http from 'node:http'; import * as https from 'node:https'; import *
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 dist/core/youtube.js
medium Hardcoded egress to an external endpoint (dist/cli/utils.js)MTC-SRC-003
In the server's implementation (`dist/cli/utils.js:28`): 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 res = await fetch('https://registry.npmjs.org/webpeel/latest', { signal: AbortSignal.timeout(200
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 dist/cli/utils.js
medium Hardcoded egress to an external endpoint (dist/core/answer.js)MTC-SRC-003
In the server's implementation (`dist/core/answer.js:121`): 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 resp = await fetch('https://api.openai.com/v1/chat/completions', { 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 dist/core/answer.js
medium Hardcoded egress to an external endpoint (dist/core/apply.js)MTC-SRC-003
In the server's implementation (`dist/core/apply.js:272`): 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 resp = await fetch('https://api.anthropic.com/v1/messages', { 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 dist/core/apply.js
medium Hardcoded egress to an external endpoint (dist/core/extract-inline.js)MTC-SRC-003
In the server's implementation (`dist/core/extract-inline.js:74`): 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 resp = await fetch('https://api.openai.com/v1/chat/completions', { 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 dist/core/extract-inline.js
medium Hardcoded egress to an external endpoint (dist/core/image-caption.js)MTC-SRC-003
In the server's implementation (`dist/core/image-caption.js:177`): 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://api.openai.com/v1/chat/completions', { method: 'POST',
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 dist/core/image-caption.js
medium Hardcoded egress to an external endpoint (dist/core/llm-extract.js)MTC-SRC-003
In the server's implementation (`dist/core/llm-extract.js:303`): 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://api.anthropic.com/v1/messages', { 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 dist/core/llm-extract.js
medium Hardcoded egress to an external endpoint (dist/core/llm-provider.js)MTC-SRC-003
In the server's implementation (`dist/core/llm-provider.js:204`): 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 resp = await fetch('https://api.openai.com/v1/chat/completions', { 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 dist/core/llm-provider.js
medium Hardcoded egress to an external endpoint (dist/core/local-search.js)MTC-SRC-003
In the server's implementation (`dist/core/local-search.js:74`): 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 res = await fetch('https://places.googleapis.com/v1/places:searchText', { method: 'POST',
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 dist/core/local-search.js
medium Hardcoded egress to an external endpoint (dist/core/search-provider.js)MTC-SRC-003
In the server's implementation (`dist/core/search-provider.js:1525`): 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.googleapis.com/customsearch/v1?${params}`, { signal: AbortSignal.
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 dist/core/search-provider.js
medium Hardcoded egress to an external endpoint (dist/core/threat-feeds.js)MTC-SRC-003
In the server's implementation (`dist/core/threat-feeds.js:29`): 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 res = await fetch('https://openphish.com/feed.txt', { signal: AbortSignal.timeout(5000),
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 dist/core/threat-feeds.js
low Hardcoded Google API key in server code (dist/core/youtube.js)MTC-SRC-008
A hardcoded Google API key (a client API key (restricted by referrer/quota, not a private secret)) appears in `dist/core/youtube.js:345`. Verify whether this is a real credential; if so, remove and rotate it.
Evidence: Google API key: AIza…(redacted)
Fix: Remove the secret, rotate it, and load credentials from the environment or a secret store.
Location: server dist/core/youtube.js
Tools 7
Each tool and what it can reach — statically extracted from the published source.
summarizeingests untrusted inputextract-productno sensitive capabilitymonitor-priceno sensitive capabilityresearchno sensitive capabilitytopicno sensitive capabilityurlno sensitive capabilityWebPeelno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (7 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Versions 1
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 |
|---|---|---|---|---|
v0.22.0 latest |
A 92/100 | 14 | 1.13.0 | 2026-09-07 |
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 webpeel --onlineOther implementations of Webpeel 1
Independent packages implementing the same tool, scanned with the same engine. Compare all 2 side by side →
More 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