Skip to main content
Glama
storefront-guard-mcp-server

storefront-guard-mcp-server

by maxigirl123

Fortik

Real-time merchant verification for agentic commerce. A shopping agent calls verify_storefront with a domain before paying, and gets back a trust score with a plain-English verdict the agent can act on — in under two seconds.

Fortik is the trust check AI shopping agents run before checkout. It doesn't ask merchants to register in advance — it gathers evidence directly, in the moment, from independent public sources.

fortik.io

This is the mirror image of merchant-side agent-verification protocols like Visa's Trusted Agent Protocol: those let a merchant confirm an incoming agent is legitimate. Fortik lets the agent confirm the merchant is legitimate before committing payment.

What it checks

  • Domain registration age & recent changes — via free public RDAP lookups. A domain registered days ago, or one whose registration data changed in the last two weeks, is a red flag.

  • SSL certificate issuance history — via free public Certificate Transparency logs (crt.sh). A cert reissued very recently on an otherwise long-established domain can indicate a takeover or hosting change, even when the domain itself looks old and trustworthy.

  • HTTPS validity — does the site currently serve a valid cert at all.

  • Known-scam blocklist — URLhaus and Google Safe Browsing.

  • Corporate registration — US entity lookup via OpenCorporates.

  • Legal name verification — GLEIF entity registry cross-check.

  • Web traffic rank — Tranco top-1M ranking.

  • Federal exclusions — SAM.gov debarment check.

  • FDA enforcement — corroborating signal when other risks are present.

Every deduction from the trust score comes with a plain-English reason in the reasons array — this is deliberately an explainable heuristic, not a black-box model.

Related MCP server: attest-mcp

Setup

Requires Node.js 18+.

npm install
npm run build

Copy .env.example to .env and fill in your keys.

Running it

As a local MCP server (stdio):

npm start

As a remote MCP server (streamable HTTP) with x402 payment:

npm run start:http
# POST http://localhost:3000/mcp

As a pay-per-call x402 HTTP API:

npm run start:x402
# POST http://localhost:4021/verify   { "domain": "example-shop.com" }

As a REST API (API key auth):

npm run start:rest
# POST http://localhost:4022/verify   { "domain": "example-shop.com" }
# Header: X-API-KEY: your-key

All three servers at once:

npm run start:all
# MCP:  http://localhost:3000/mcp
# x402: http://localhost:4021/verify
# REST: http://localhost:4022/verify

Feedback endpoint

Submit outcome data after a transaction to help build training data for future ML scoring:

POST http://localhost:4022/feedback
Header: X-API-KEY: your-key
Body: { "domain": "example-shop.com", "outcome": "legit" | "scam" }

How to use the recommendation field

Every verification result includes a top-level recommendation string alongside the numeric trustScore. Agents should branch on it rather than implementing their own threshold logic against the raw score.

Value

Suggested agent behavior

proceed

Complete the transaction silently. Trust score is low-risk with high confidence.

pause_for_confirmation

Stop before paying and show recommendationReason to the user.

do_not_proceed

Block the transaction and actively notify the user — do not fail silently.

recommendationReason is a one-line plain-English explanation safe to show directly to users.

Pricing

$0.01/call via x402. Set your wallet address in PAY_TO_ADDRESS and network in X402_NETWORK (default: base).

Environment variables

Variable

Required

Description

PAY_TO_ADDRESS

Yes (x402)

Your wallet address for USDC payments

X402_NETWORK

No

Blockchain network (default: base)

PRICE_USD

No

Per-call price (default: 0.01)

API_KEYS

Yes (REST)

Comma-separated valid API keys

GOOGLE_SAFE_BROWSING_API_KEY

No

Degrades gracefully if unset

SAM_GOV_API_KEY

No

Degrades gracefully if unset

URLHAUS_AUTH_KEY

No

Degrades gracefully if unset

FEEDBACK_LOG

No

Path for feedback JSONL log (default: feedback.jsonl)

MCP_PORT

No

MCP server port (default: 3000)

X402_PORT

No

x402 server port (default: 4021)

REST_PORT

No

REST API port (default: 4022)

Available Tools

1 tool
verify_storefrontVerify Storefront LegitimacyA
Read-only

Checks whether a merchant storefront looks like the same legitimate entity it appeared to be recently, BEFORE an agent commits payment to it.

This is the mirror image of merchant-side agent-verification protocols (e.g. Visa's Trusted Agent Protocol): those let a merchant confirm an incoming agent is legitimate. This tool lets the AGENT confirm the MERCHANT is legitimate before paying.

It does NOT guarantee a storefront is safe - it is a fast, explainable pre-purchase signal built from free public data sources (domain registration history via RDAP, SSL certificate issuance history via Certificate Transparency logs, HTTPS validity, and a known-scam-domain check). Treat a "high" risk result as a strong reason to pause and get human confirmation before paying, and a "low" risk result as one input among others, not a guarantee.

Args:

  • domain (string): the bare domain of the storefront to check, e.g. "example-shop.com"

Returns: { "domain": string, "trustScore": number, // 0-100, higher = more trustworthy "riskLevel": "low" | "medium" | "high" | "unknown", "confidence": "low" | "medium" | "high", // how many signals could actually be resolved "reasons": string[], // human-readable explanation for the score "recommendation": "proceed" | "pause_for_confirmation" | "do_not_proceed", "recommendationReason": string, // one-line explanation of why this recommendation was made "signals": { ...raw signal data for audit/debugging... }, "checkedAt": string // ISO timestamp - this is a point-in-time result, do not cache it }

Recommendation values and suggested agent behavior:

  • "proceed": trust score is high with high confidence — complete the transaction silently, no user confirmation needed

  • "pause_for_confirmation": score is borderline or confidence is insufficient — pause and show recommendationReason to the user before completing payment

  • "do_not_proceed": domain matched a scam list or trust score is critically low — block the transaction and actively notify the user (do not fail silently)

Examples:

  • Use when: an agent is about to submit payment to a storefront it found via search or a marketplace listing

  • Use when: comparing several candidate storefronts for the same product before choosing one to buy from

  • Don't use when: verifying a well-known, previously-transacted-with merchant on every single repeat purchase - reserve for new or unfamiliar storefronts, since results are not meant to be cached long-term but also aren't needed for every routine repeat transaction

Error Handling:

  • Never throws - if a data source is unreachable, the affected signal is returned as null and "confidence" drops accordingly rather than failing the call

Inputs: domain (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.6/5.0

    Scored across 1 tool

    Disambiguation5/5

    With only one tool, there is no possibility of confusion or overlap. The tool's purpose is singular and clearly defined, so agents cannot misselect between alternatives.

    Naming Consistency5/5

    The single tool name 'verify_storefront' follows the verb_noun pattern consistently. With one tool, there are no naming inconsistencies or mixed conventions to evaluate.

    Tool Count3/5

    The server has only one tool, which feels thin for a domain that could reasonably include additional operations like reporting a scam or checking verification history. However, the narrow purpose of storefront verification is adequately covered by this single comprehensive tool, making it borderline appropriate.

    Completeness5/5

    For the stated purpose of pre-purchase storefront verification, the tool covers all necessary signals (domain registration, SSL, HTTPS, scam list) and returns actionable recommendations. There are no obvious gaps or dead ends for the defined use case.

    Maintenance

    ActivitySlowing
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      Enables AI agents to scan payment endpoints for safety, returning a letter grade (A–F) and verdict before authorizing payments.
      2
      34 npm
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Provides AI agents with zero-cost, zero-dependency trust evaluation for domains, URLs, wallets, APIs, and IPs, returning a 0-100 score with SSL, DNS, WHOIS, security header, and content sub-scores, plus batch comparison to rank multiple targets.
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      Enables AI agents to verify links and payments for scam risk before acting, returning deterministic allow/ask/deny verdicts with scores, reasons, and warnings using local checks.
      3
      23 PyPI
      1
      MIT