ToolTrust
D57/100
Smithery

onchaintel-pqs

mcpsmithery

@Smithery

The world's first named AI prompt quality score. Score any LLM prompt before it hits any model — returns grade (A-F), score out of 40, percentile, and dimension breakdown across 8 quality dimensions. Built on PEEM, RAGAS, G-Eval, and MT-Bench frameworks. **Tools:** - score_prompt — Free. No API key needed. - optimize_prompt — $0.025 USDC. Returns optimized prompt + full breakdown. - compare_models — $0.50 USDC. Claude vs GPT-4o head-to-head. Cheaper than one bad inference call.

By Smithery | 8 findings | Scanned 4/19/2026 | tooltrust-scanner/v0.3.8

1 Critical3 High1 Low3 Info

Risk Summary

Block in Production

Dep Visibility + Secret Handling risk is significant. Avoid using this in production agents.

Potential impact: This finding indicates the tool should be reviewed before it is trusted.

Recommended action: This tool should stay disabled in production agents until the flagged risks are fixed and the scan is clean.

{
  "mcpServers": {
    "onchaintel-pqs": {
      "disabled": true
    }
  }
}

Security Findings (8)

  • CriticalAS-006

    💻Arbitrary Code Execution

    heuristic signal

    optimize_prompt:tool name or description implies arbitrary script/code execution (evaluate_script, execute javascript, etc.)

    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.

  • HighAS-002

    ⚠️Excessive Permissions

    optimize_prompt:tool declares exec permission

    Fix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.

  • HighAS-010

    🔑Insecure Secret Handling ×2

    input parameter "api_key" appears to accept a secret or credential

    optimize_promptcompare_models

    Fix: Avoid accepting raw credentials as input parameters. Use secret managers (e.g. 1Password CLI, AWS Secrets Manager) and ensure credentials are never logged or stored in agent traces.

  • LowAS-011

    ℹ️Missing Rate-Limit / Timeout

    optimize_prompt: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.

  • InfoAS-014

    ℹ️Dependency Inventory Unavailable ×3

    Tool did not expose metadata.dependencies or repo_url, so supply-chain coverage is limited.

    score_promptoptimize_promptcompare_models

    Fix: Review and remediate the identified issue.

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 onchaintel-pqs"

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.

[![ToolTrust Grade D](https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-directory/main/docs/badges/grade-d.svg)](https://github.com/AgentSafe-AI/tooltrust-directory)