Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

io.github.MetaLift-AI/metalift

NPM · @METALIFT/MCP

Metalift MCP for AI agents: web search (2 credits), scrape, crawl, and map tools

Available components

0 this week 73 Trust /100

Last scanned (16 hours ago)

Scores higher than 46% of npm servers

Category Web Scraping

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security81
  • No malware found by supply-chain analysis.Pass
  • CVE check failed: a known high-severity CVE affects zod 3.25.76, a direct dependency. A fixed version is available. View diagnostics → Fail
  • No install/post-install scripts declared.Pass
  • 31 of 93 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency6
  • Repository check failed: the declared repository URL redirects; it must resolve directly. See how to fix → View diagnostics → Fail
  • Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
  • Licence could not be checked: the licence is shipped as a file inside the package, not declared as a standard (SPDX) licence identifier, so we cannot tell whether it is OSI-approved.Unverified
  • Actively maintained (last published 62 days ago).Pass
  • Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability85
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 1613 tokens (~115/item across 14 items; 11 tools + 3 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage97
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 91% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 11 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 13 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
What we tested

Checks we ran (15)

  • Malware scan
  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • Maintenance
  • Security disclosure
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Checks we could not complete (1)

These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • License in Provenance & TransparencyLicence could not be checked: the licence is shipped as a file inside the package, not declared as a standard (SPDX) licence identifier, so we cannot tell whether it is OSI-approved.

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 20 Nov 26 +1
    • Stability: 0.97 → pass security
  • 18 Nov 26 −1
    • Stability: pass → 0.93 functional
  • 12 Nov 26 +1
    • Stability: 0.97 → pass security
  • 10 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

  • 9 Nov 26 −2
    • Stability: pass → 0.90 functional
  • 3 Nov 26 +1
    • Stability: 0.97 → pass security
  • 2 Nov 26 −1
    • Stability: pass → 0.97 functional
  • 1 Nov 26 0
    • Security disclosure: unverified → fail ▼ functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Analysed npm/@metalift/mcp@1.0.15

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Vulnerabilities 1 finding
ID CVE Severity Vector Fix available
GHSA-mrhx-c7xc-m3w5 CVE-2023-54404 high CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H yes

Background: What a vulnerability scan can and cannot prove →

Dependencies 93 packages
Packages resolved 93
Stale 31
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 11 exposed · ~1,361 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
metalift_batch_scrape ~146

Scrape up to 100 URLs in parallel (billed per URL). Default response_detail=compact. Use async=true for background jobs; wait=true blocks with progress. For JS-heavy pages set strategy=auto in scrape_options. You are solely responsible for complying with website terms, robots.txt, copyright, and data protection laws when using scraped content.

NameTypeReqDescription
asyncboolean–Run as background job (returns job id)
scrape_optionsobject–Shared scrape options applied to every URL in the batch
urlsarrayyesURLs to scrape in parallel
waitboolean–When async=true, wait for completion with progress updates (default true).

No output schema declared.

No examples provided.

metalift_crawl ~131

Crawl a site from a seed URL and return markdown for discovered pages (1+ credits per page). Default wait=true blocks with progress; wait=false returns job id for metalift_job_status.

NameTypeReqDescription
exclude_pathsarray–Skip paths matching these prefixes
include_pathsarray–Only crawl paths matching these prefixes
limitnumber–Maximum pages to crawl
max_depthnumber–Maximum link depth from seed URL
urlstringyesSeed URL to start crawling from
waitboolean–Wait for crawl to finish with progress updates (default true).

No output schema declared.

No examples provided.

metalift_job_status ~52

Poll async crawl or batch job status and results. Returns human-readable progress (pages completed, credits charged).

NameTypeReqDescription
job_idstringyesJob id from metalift_crawl or metalift_batch_scrape

No output schema declared.

No examples provided.

metalift_list_sessions ~23

List org-scoped browser sessions stored via metalift_seed_session.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

metalift_list_strategies ~29

List scrape strategies with protection levels and credit estimates. Use before scraping unknown protected sites.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

metalift_map ~77

Discover same-origin links by parsing HTML anchors on one page (1 credit). Fallback when metalift_sitemap is unavailable. Does not fetch full page content.

NameTypeReqDescription
limitnumber–Maximum URLs to return
searchstring–Optional substring filter for URLs
urlstringyesPage URL to extract links from

No output schema declared.

No examples provided.

metalift_scrape ~400

Scrape a single URL into markdown, HTML, or text. Default: fast static article path (1 credit, response_detail=compact). E-commerce hosts auto-route to retail/residential. Pass strategy=auto for WAF/SPA pages. Fetch metalift://agent-guide for session workflow. You are solely responsible for complying with website terms, robots.txt, copyright, and data protection laws when using scraped content.

NameTypeReqDescription
cookie_headerstring–Raw Cookie header from DevTools. Routes through Playwright + sticky proxy to preserve browser TLS fingerprint. Prefer metalift_seed_session with storage_state for repeat scrapes.
cookiesobject–Session cookies (name→value). Routes through Playwright browser session + proxy — not static HTTP. Prefer metalift_seed_session for reuse.
formatsarray–Output formats; default markdown only
headersobject–Extra request headers. Pass User-Agent from the user's browser when using cookie_header so the session fingerprint matches.
only_main_contentboolean–Extract main article content only (default true)
proxystring–Proxy tier; default direct for static pages
renderstring–Render mode; default static for plain URLs
response_detailstring–Response depth: compact (default, ~16k chars, no links), standard (full markdown + capped links), full (complete JSON).
screenshotboolean–Capture page screenshot (adds cost)
strategystring–Scrape strategy: auto, article, spa, cloudflare, authenticated, listing, retail, jsonld, download, raw, or comma-separated chain. Use download for full static HTML. See /v1/strategies for protection…
timeout_msnumber–Per-attempt timeout in milliseconds
urlstringyesPage URL to scrape
wait_forstring–CSS selector to wait for before scraping

No output schema declared.

No examples provided.

metalift_seed_session ~151

Store browser session credentials for a domain (org-scoped). Prefer full Playwright storage_state JSON from the user's browser — preserves cookies + localStorage for fingerprint-coherent replay via unified browser session on later scrapes. Fallback: cookie_header + user_agent from DevTools.

NameTypeReqDescription
cookie_headerstring––
cookiesobject––
domainstringyesSite hostname, e.g. actionpowertest.com or www.walmart.com
storage_stateobject–Playwright context.storageState() JSON — preferred over cookie_header alone
ttl_hoursnumber––
user_agentstring–User-Agent from the same browser session that issued the cookies

No output schema declared.

No examples provided.

metalift_sitemap ~128

Fetch XML sitemap URLs for a site. Discovers sitemap locations from robots.txt (Sitemap: directives) or /sitemap.xml, follows sitemap indexes, and returns page URLs with optional lastmod/changefreq/priority. Costs 1 credit. Prefer this over metalift_map when you need the site's published URL list.

NameTypeReqDescription
limitnumber––
same_originboolean–Only return URLs on the same origin (default true)
searchstring–Optional substring filter; matching URLs sort first
urlstringyesSite homepage or direct sitemap.xml URL

No output schema declared.

No examples provided.

metalift_warm_session ~117

Automated browser warmup to collect cookies for later scrapes (15 credits). Use when manual metalift_seed_session is not possible; often fails on strict WAFs.

NameTypeReqDescription
domainstring–Override domain for stored session
proxystring–Default auto. Use residential for WAF-heavy sites.
strategystring–e.g. retail, cloudflare, authenticated
timeout_msnumber–Browser warmup timeout in milliseconds
urlstringyesSeed URL to visit in browser

No output schema declared.

No examples provided.

metalift_web_search ~107

Search the web and return up to 10 SERP results (title, url, snippet, engine, score). Costs 2 credits per search. Returns search snippets only — not page content. Answer simple questions from snippets; do not auto-scrape. Call metalift_scrape separately only when full page content is required.

NameTypeReqDescription
categoriesarray–Optional search categories
languagestring–Result language (default en)
querystringyesSearch query

No output schema declared.

No examples provided.

Install

How do I install the io.github.MetaLift-AI/metalift MCP server?

io.github.MetaLift-AI/metalift runs locally as an npm package, launched with npx -y @metalift/mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · @metalift/mcp

# add to Claude Code
claude mcp add metalift-ai-metalift -- npx -y @metalift/mcp
Common questions

What is the io.github.MetaLift-AI/metalift MCP server?

io.github.MetaLift-AI/metalift is an MCP server listed in the public MCP registry as io.github.MetaLift-AI/metalift. Metalift MCP for AI agents: web search (2 credits), scrape, crawl, and map tools. This page covers its npm package (@metalift/mcp).

Is the io.github.MetaLift-AI/metalift MCP server safe to use?

io.github.MetaLift-AI/metalift scores 73 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 21 November 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the io.github.MetaLift-AI/metalift MCP server expose?

io.github.MetaLift-AI/metalift exposes 11 tools: metalift_scrape, metalift_batch_scrape, metalift_crawl, metalift_sitemap, metalift_map, and 6 more. Their descriptions and schemas cost roughly 1,361 tokens of context every time the server is loaded.

Is the io.github.MetaLift-AI/metalift MCP server still maintained?

io.github.MetaLift-AI/metalift is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the io.github.MetaLift-AI/metalift MCP server?

VerifyMCP ran 15 checks on io.github.MetaLift-AI/metalift, covering Malware scan, Known CVEs, Install scripts, Dependency health and 11 more. One item could not be completed, a gap on our side rather than a finding about io.github.MetaLift-AI/metalift: License. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.