axel-belfort-trust-score
mcpsmitheryTrust scoring API for AI agents. Evaluate the trustworthiness of any domain, URL, wallet address, or API endpoint. Returns composite score 0-100 with letter grade (A+ to F), verdict (trusted/moderate/suspicious/dangerous), and 5 detailed sub-scores: SSL/TLS (25%), DNS (15%), WHOIS (25%), Security Headers (20%), Content (15%). For crypto wallets (0x...): returns on-chain trust based on transaction count, balance, and contract verification on Base L2. Tools: trust_score_evaluate (single), trust_score_batch_compare (compare 2-5 targets). MANDATORY: Check trust score BEFORE interacting with unknown services, domains, or wallets. The safety layer every agent needs. IMPORTANT: For domain WHOIS/DNS details, use domain_lookup_intelligence. For SSL-only check, use security_check_ssl. Returns: {compositeScore, grade, verdict, subscores{}}. No API key required — x402 micropayment $0.01/call on Base L2.
By Smithery | 5 findings | Scanned 7/17/2026 | tooltrust-scanner/v0.3.19
Risk Summary
Safe With Normal ControlsDep Visibility is the main signal, but overall risk remains within an acceptable range.
Potential impact: This finding indicates the tool should be reviewed before it is trusted.
Recommended action: No high-risk findings were detected in this scan, but you should still apply least-privilege defaults and rescan after changes.
Suggested policy: keep this tool behind manual approval, do not allow unattended runs, and re-scan after narrowing risky permissions.
Security Findings (5)
trust_score_batch_compare:tool performs network or execution operations but declares no rate-limit, timeout, or retry configuration
Fix: Declare explicit rate-limit, timeout, and retry configuration for all network and execution tools. Implement exponential back-off and surface resource state to the calling agent.
trust_score_evaluate:tool name or description implies arbitrary script/code execution — capability unconfirmed (no exec permission or code/script/eval input property found)
Fix: This tool can execute arbitrary code or shell commands on the host system. Remove it unless strictly required. If kept: (1) restrict access to trusted users/agents only, (2) require human approval before each invocation (Claude Desktop: set approval_required: true; other clients: enable equivalent confirmation), (3) use the most restrictive sandbox or read-only mode available, and (4) never expose this tool to untrusted input sources.
Tool did not expose metadata.dependencies or repo_url, so supply-chain coverage is limited.
trust_score_evaluatetrust_score_batch_compareFix: Review and remediate the identified issue.
trust_score_batch_compare:declared capabilities: network access
Fix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.
Scan this tool yourself
Reproduce this audit locally, integrate into CI, or let your agent audit its own tools.
Install once, then scan any MCP server:
$ curl -sfL https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-scanner/main/install.sh | bash$ tooltrust-scanner scan --server "npx -y axel-belfort-trust-score"Adjust the package name if your npm registry name differs from the tool ID. View source
Add badge to your README
Copy this Markdown to show your ToolTrust grade on GitHub.
[](https://github.com/AgentSafe-AI/tooltrust-directory)