Skills/npm/alterlab-mcp-server

alterlab-mcp-server@1.13.20

VERIFIED

Publisher claims: "MCP server for web scraping, structured data extraction, and screenshots — give Claude, Cursor, Windsurf, and AI agents the ability to scrape any website with automatic anti-bot bypass" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher rapiercraft · publishing for 277 daysInstalls 10,180Last detonated 3d ago
$claude mcp add alterlab-mcp-server -- npx -y alterlab-mcp-server
WatchReport an issue

Coverage

Started with a decoy ALTERLAB_API_KEY; tool list observed. Tool calls with a real credential not tested.
Tested
server startup with a tagged decoy in ALTERLAB_API_KEY · MCP initialize and tools/list · every tool description, for hidden instructions · where the decoy credential went · every file read, file written and host contacted by what ran
Not tested
what the tools do when called with a real credential
Needs
ALTERLAB_API_KEY — give it to the server where it runs, through vet-skills run --secrets, so the value never enters the server's environment. Never paste a credential into a chat, a ticket or a report.

Before you give it your token

It will ask for
ALTERLAB_API_KEYConfiguration, not credentials: ALTERLAB_API_URL
Where it talks to
alterlab.io (its own)
What the honeypot saw
no credential files read · no network
What we could not test
what the tools do when called with a real credential

Connect it with a scoped credential, under the guard. It asks for ALTERLAB_API_KEY and talks to alterlab.io. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind.

$vet-skills run --secrets ALTERLAB_API_KEY=alterlab.io -- npx -y alterlab-mcp-server

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-11 and scored it 83/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 45 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
4.4sprocessdependency install exit 0
24sprocessrelaunched with a decoy ALTERLAB_API_KEY (tagged; nothing real)
44sclaimed26 tools with a decoy ALTERLAB_API_KEY: alterlab_scrape, alterlab_extract, alterlab_screenshot, alterlab_get_job, alterlab_estimate_cost, alterlab_check_balance, alterlab_get_usage, alterlab_crawl, alterlab_crawl_status, alterlab_crawl_cancel, alterlab_search, alterlab_map, alterlab_batch_scrape, alterlab_batch, alterlab_batch_status, alterlab_list_sessions, alterlab_create_session, alterlab_get_session, alterlab_update_session, alterlab_refresh_session, alterlab_validate_session, alterlab_delete_session, alterlab_list_beta_features, alterlab_list_my_beta_features, alterlab_enable_beta_feature
44sprocessscript backend runs setup only
44sprocessno install scripts to re-run

Static findings

MEDIUM
Process kill commanddist/shared/tool-definitions.json:4224 · Process kill command — agent can terminate processes… grant started; an agent cannot lift a pause the user set, and takeover and the kill switch are available only from the user's own dashboard session.", "…Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packagedist/auth.js:373 · npx invocation of non-well-known package — may execute untrusted code" npx -y alterlab-mcp-server",Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Tool description instructs the agent: section addressed to the agentmcp:tools/alterlab_extract:2 · Instruction aimed at the agent: section addressed to the agenth":2000,"description":"Natural language instructions for LLM extraction (e.g., 'Extract all product prices and ratings')Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Prompting user to enter sensitive credentialsdist/auth.js:234 · Prompting user to enter sensitive credentials — social engineering" Paste your API key: ",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03

Cost to the agent

Instructions loaded
≈86 tok
1 file · 54 in bundle
Tool list per prompt
≈18,088 tok
26 tools · 696 per tool
Handshake
1198 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 398

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

No advisories in OSV for alterlab-mcp-server@1.13.20 as of 3d ago. This is the package itself, not its dependencies.