LinkVouch
Optional Google Safe Browsing API key adds a blocklist check when vetting links, in addition to the built-in URL, redirect and domain heuristics.
Checks npm packages against registry metadata: whether the package exists, whether the name is a near-typo of a popular package, its age and download counts, and whether it runs install scripts.
Checks PyPI packages against registry metadata: existence, near-typo names of popular packages, age and download counts, and install-script behaviour.
Used by the official-site verification tool: looks up an organisation's official domain via Wikidata (in addition to a built-in brand list) and reports whether a given URL matches that domain.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
LinkVouch
An MCP connector that lets Claude (or any MCP client) check links, scam messages, "official" websites and software packages before recommending them.
It was built for one problem in particular: AI-recommendation poisoning. Attackers plant content so that AI assistants recommend their fake login pages, fake support numbers, or malicious packages with invented names ("slopsquatting"). LinkVouch gives the assistant a way to check first.
Status: early version (0.1). Heuristics, not a guarantee. See Limits.
Tools
Tool | What it does |
| Run before an assistant presents a link, package or support phone number. Confirms a link really belongs to the brand it claims, checks packages, and refuses to vouch for phone numbers. |
| Look-alike and typo domains ( |
| Scam patterns in an SMS, email or chat (urgency, OTP or card requests, threats, prizes, payment requests) plus a check of every link. Includes Singapore rules: banks there do not send clickable links, and government links live on |
| Finds an organisation's official domain from a built-in brand list and Wikidata, and says whether a URL matches it. |
| npm and PyPI: does the package exist at all, is the name a near-typo of a popular package, how old is it, how many downloads, does it run install scripts. |
Every result has a verdict (high_risk, suspicious, no_red_flags, known_official_domain), a list of plain-language findings, and advice.
Related MCP server: Mnemom
Run it
Needs Node.js 24 or newer (it runs the TypeScript files directly, no build step).
npm installnpm testnpm test runs the offline tests and then the end-to-end tests, which need internet. npm run test:unit runs only the offline ones. npm run typecheck checks the TypeScript types. GitHub Actions runs all three on every push and pull request.
Local (Claude Code / Claude Desktop): the client starts the server itself.
claude mcp add linkvouch -- node /absolute/path/to/linkvouch/src/stdio.tsHosted (Claude custom connector): run the HTTP server somewhere public with HTTPS.
npm startThe endpoint is POST /mcp (stateless Streamable HTTP), and GET /healthz answers {"ok":true} for health checks. The server reads PORT.
To deploy on Render, the repository includes a render.yaml Blueprint: in the Render Dashboard choose New → Blueprint and pick your copy of this repository. On Railway or Fly.io, set the start command to npm start.
Then in Claude: Settings → Connectors → Add custom connector → https://your-host/mcp.
Optional environment variables:
Variable | Purpose |
| HTTP port (default 3000) |
| Requests per client IP per minute (default 60) |
| Number of reverse proxies in front of the server (default 1). Used to find the client IP for rate limiting. |
| Upper limit for one request in milliseconds (default 30000) |
| A URL added to the client name sent to public APIs (Wikimedia asks for this) |
| Google Safe Browsing key, adds a blocklist check. The Safe Browsing API is for non-commercial use; use Google's Web Risk API for a paid service. |
How it stays safe itself
A tool that fetches user-supplied URLs is a classic target, so:
No internal requests (SSRF): every hop of every redirect is resolved and refused if it points at a private, loopback, link-local, CGNAT or cloud-metadata address. Only
http/httpson ports 80, 443, 8080, 8443.Pinned addresses (DNS rebinding): each hop's name is looked up once, and the connection goes to exactly the address that was checked. A DNS server cannot answer "public" for the check and "internal" for the request.
No page content: only the status code and
Locationheader are read. Bodies are discarded.Bounded: 6 seconds per redirect hop and 15 seconds per redirect chain, at most 5 redirects, at most 5 links per message, input length limits, and (hosted) 30 seconds per request.
No storage: nothing about requests is saved or logged. Rate limiting is in memory.
Read-only tools: all tools are marked read-only.
Limits
Please read these before relying on it.
no_red_flagsis not "safe". A brand-new scam on a clean-looking domain can pass every check.The brand list is short (about 35 brands, weighted to Singapore). Brands outside it get fewer checks.
Companies own domains that are not in the list or on Wikidata, so
mismatchmeans "not confirmed", not "definitely fake". Expect some false alarms, e.g. a legitimate site whose name contains a brand name.Wikidata is community-edited and name searches can return a different organisation with a similar name.
Domain age is unavailable for registries without RDAP (including
.sg).Package checks read registry metadata only. The code inside a package is not scanned.
Links on unusual ports are not contacted at all (reported as
unusual_port), so redirects and reachability are unknown for them.The hosted mode has no authentication yet. Anyone with the URL can use it (within the rate limit).
The rate limit is per IP address. Clients that reach the server through a shared service share one limit, and
TRUST_PROXY_HOPSmust match the host's setup for the limit to see the right address.On a free hosting plan the server sleeps when idle. On Render's free plan the first request after 15 idle minutes takes about a minute, which can be longer than a client is willing to wait.
Roadmap
Larger, community-maintained brand list
More ecosystems (crates.io, Go modules, Docker Hub) and browser-extension IDs
OAuth and usage tiers for the hosted version
A plain web page for people who do not use an MCP client
Responsible use
LinkVouch only looks at public information (DNS, RDAP, HTTP status, public registries). Do not point it at systems you have no reason to check, and report real scams to the proper channel (in Singapore: ScamShield, 1799).
Licence
MIT. See LICENSE.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Free safety checks for AI agents: links, sites, MCP servers, and pages read with traps removed.
See which AI models fall for traps in everyday jobs, and check or scan any MCP server, skill or package before your agent installs it. No sign-in; read-only; returns structured data.
Scam and phishing detection for AI agents: safe/warn/danger verdicts for URLs and messages.
Check a link, a message or a web page for scams and phishing before you or your agent act.
Related MCP Servers
- AlicenseAqualityCmaintenanceScans suspicious messages, URLs, and text for scams inside any MCP-compatible AI assistant. No signup or API key needed for anonymous use.160 npmMIT
- FlicenseNot gradedqualityCmaintenanceProvides trust infrastructure for AI agents by enabling reputation lookup, website trust scanning, and identity verification via MCP tools.1-
- AlicenseNot gradedqualityBmaintenanceEnables Alexa+ and other MCP-capable assistants to voice-check suspicious messages, links, and phone numbers, with guided call interviews, official-source verification, and plain-language scam briefings.MIT
- AlicenseNot gradedqualityCmaintenanceEnables users to check suspicious text, emails, marketplace listings, job offers, investment pitches, and links through MCP tools, returning an assessment with supporting checks and next-step guidance.Apache 2.0