Trust Score API

io.github.Br0ski777Published by GitHub account Br0ski777v1.1.0Updated Oct 24, 2026

Trust scoring for domains, wallets, APIs. SSL+DNS+WHOIS+headers. Score 0-100.

VerifiedSSEWeb executableFinanceSecurity & Monitoring

Overview

AI-generated overview

Remote MCP server that scores the trustworthiness of domains, URLs, API endpoints and crypto wallets on a 0-100 scale with sub-scores and a verdict.

What you can do
Evaluate a single domain, URL, IP address or wallet address and get a 0-100 composite score, letter grade, verdict and five sub-scores (SSL, DNS, WHOIS, security headers, content). Optionally limit which checks run for faster results. Compare 2-5 targets side by side and get them ranked from most to least trusted.
When to use it
Useful when an assistant is about to interact with an unfamiliar domain, API endpoint or wallet and you want a quick safety signal before paying, sending sensitive data or trusting the service. Also handy for choosing the safest option among several candidates.
Requirements
A remote SSE endpoint; no local runtime, API key or signup. Calls are paid per use via the x402 protocol in USDC on Base L2, so an x402-capable client with a funded wallet is needed to complete the payment challenge.
Before you install
Each call costs money ($0.02 for a single evaluation, $0.03 for a batch) and requires signing a USDC payment on Base, so a wallet and spending are involved. Scores are third-party assessments, not guarantees. The targets you submit are sent to the remote service.

Installation

In SourceWeft

  1. Open Trust Score API in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via SSE. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.Br0ski777%2Ftrust-score/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "trust-score-api": {
      "type": "sse",
      "url": "https://trust-score.api.klymax402.com/mcp"
    }
  }
}

README

Trust Score API

[MCP Server] [x402] [License: MIT]

Evaluate trustworthiness of any domain, URL, wallet, or API. Returns 0-100 score with 5 sub-scores: SSL, DNS, WHOIS, security headers, content. Zero-cost, zero-dependency. The trust layer agents need before interacting with unknown services. Pay-per-call via x402 (USDC on Base L2) -- no API key, no signup, no rate-limit wall.

Part of the klymax402 marketplace -- 100 x402 micropayment APIs for AI agents, one wallet, USDC on Base.

Quickstart -- MCP

Add to your MCP client config (Claude Desktop, Cursor, ElizaOS, etc.):

json
{  "mcpServers": {    "trust-score": {      "url": "https://trust-score.api.klymax402.com/mcp"    }  }}

Quickstart -- HTTP (x402)

bash
curl -X POST "https://trust-score.api.klymax402.com/api/score" \  -H "Content-Type: application/json" \  -d '{"target":"..."}'# -> 402 Payment Required, with an x402 payment challenge in the response body

Any x402-aware client (@x402/fetch, x402-agent-tools, ATXP) handles the 402 -> sign -> retry cycle automatically.

Tools

ToolMethodPathPriceDescription
trust_score_evaluatePOST/api/score$0.02Evaluate trust of a domain, URL, wallet address, or API endpoint. Returns composite score 0-100 with grade (A+ to F), verdict (trusted/moderate/suspicious/dangerous), and 5 detailed sub-scores.
trust_score_batch_comparePOST/api/batch$0.03Compare trustworthiness of 2-5 targets side by side. Returns all scores ranked from most to least trusted.

trust_score_evaluate

Use this when you need to check if a domain, website, API endpoint, or crypto wallet is safe to interact with. Returns a composite trust score 0-100 with letter grade (A+ to F), verdict (trusted/moderate/suspicious/dangerous), and 5 sub-scores:

Parameters

NameTypeRequiredDescription
targetstringyesDomain (example.com), full URL (https://api.example.com/v1), wallet address (0x...), or IP address to evaluate
checksarraynoWhich checks to run. Default: all. Pass a subset like ["ssl","dns"] for faster results (under 2s). Full scan takes 3-8s.

Example response:

json
{ compositeScore: 82, grade: "A", verdict: "trusted", subscores: { ssl: { score: 90, ... }, dns: { score: 85, ... }, ... } }

When to use: making payments, sending sensitive data, or trusting any external service. Essential for agent safety.

Not for: SEO analysis (use seo_audit_page), email validation (use email_verify_address), tech stack detection (use website_detect_tech_stack), port scanning (use network_scan_ports).

trust_score_batch_compare

Use this when you need to compare the trustworthiness of multiple domains, URLs, or wallets and pick the safest option. Accepts 2-5 targets and returns trust scores for all, sorted from most to least trusted.

Parameters

NameTypeRequiredDescription
targetsarrayyesList of 2-5 domains, URLs, or wallet addresses to evaluate and rank

Not for: single targets (use trust_score_evaluate).

Example agent prompts

  • "Check if a domain, website, API endpoint, or crypto wallet is safe to interact with"
  • "Compare the trustworthiness of multiple domains, URLs, or wallets and pick the safest option"

Payment

  • Protocol: x402 -- HTTP-native pay-per-call, no signup, no API key
  • Network: Base L2 (eip155:8453)
  • Asset: USDC
  • Facilitator: Coinbase CDP (primary), PayAI (fallback)
  • Also reachable via ATXP (OAuth-wrapped x402, RFC 9728 protected-resource metadata)

Part of klymax402

100 x402 micropayment APIs for AI agents -- one wallet, USDC on Base, zero signup.

License

MIT

Source: README.md at commit cd87d15

Tools

0
SourceWeft has not read this server's tools yet.

Version history

1
  1. v1.1.0LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declaredRequired10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts