Is ai.certscore/mcp safe to use?

ai.certscore/mcp has a Veragent trust score of 58% (Heuristic score (static analysis only)). This reflects static analysis only; a behavioral sandbox audit has not been run yet. Review the source before installing in production.

What does the Veragent trust score for ai.certscore/mcp mean?

Veragent is an independent trust layer for MCP tools. A Heuristic score comes from static analysis; SGC Certified means the tool passed a behavioral sandbox audit. Higher is safer.

🔌

ai.certscore/mcp

Queued from an install request (@certscore/mcp)

MCPDeveloper Toolsby Install-request (unclaimed) →

Heuristic Score

Trust Verdict

Low Trust58% trust score

Heuristic Score: Static analysis passed · Behavioral sandbox pending

Audit Confidence

90%

Install in Claude Desktop

⚠ Heuristic Score only — behavioral sandbox not yet run. Review source code before installing in production.

Copy the MCP config and paste it into your Claude Desktop mcp_settings.json.

{
  "agent_id": "agent-req-78d63cb6",
  "agent_name": "ai.certscore/mcp",
  "trust_score": 0.576,
  "audit_status": "inconclusive",
  "mcp_config": {
    "mcpServers": {
      "ai.certscore/mcp": {
        "command": "npx",
        "args": [
          "-y",
          "@certscore/mcp"
        ]
      }
    }
  },
  "package_binding": "unverified",
  "instructions": "Add the 'mcpServers' block to ~/.cursor/mcp.json (Cursor) or ~/Library/Application Support/Claude/claude_desktop_config.json (Claude Desktop)."
}

Audit Report

Status

Heuristic Score

Confidence

90%

Audit Cases

Report ID

l2-c102126a-9d93-4423-ac19-a1349365a458

Last Audited

2026-09-04T10:42:35.291018

Ruleset Version

sgc-layer1-2026.03

How to improve this trust score

Actionable steps from our static analysis. Address these and re-submit to raise the score.

Capabilities

Few or no concrete features listed.

→ List the specific capabilities/tools your server exposes.

Discoverability

Few tags — reduces matchability in search and recommendations.

→ Add 3+ relevant tags (domain, language, use case).

Source transparency

No public source repository detected.

→ Link a public GitHub repo so users and the audit can verify the code.

MCP endpoint

No MCP handler URL provided.

→ Provide the MCP handler/connection URL so the tool is installable.

Trust Badge

Embed this badge in your README to show your Veragent trust score:

Markdown

[![Veragent Trust](https://veragent.store/api/v1/governance/marketplace/agents/agent-req-78d63cb6/badge)](https://veragent.store/agents/agent-req-78d63cb6?utm_source=badge&utm_medium=readme)

HTML

<a href="https://veragent.store/agents/agent-req-78d63cb6?utm_source=badge&utm_medium=readme"><img src="https://veragent.store/api/v1/governance/marketplace/agents/agent-req-78d63cb6/badge" alt="Veragent Trust Badge" /></a>

Technical DetailsRaw trust signals, training provenance

Trust Signals

audit_status (raw): inconclusive
sgc_risk_tier: —
trust_score: 0.5760
sgc_risk_score: —
sgc_confidence: 0.9000
sgc_audit_cases: 0
sgc_report_id: l2-c102126a-9d93-4423-ac19-a1349365a458
sgc_rule_layer_version: sgc-layer1-2026.03
last_audited_at: 2026-09-04T10:42:35.291018
last_updated: 2026-09-04T10:38:54.066521

Canonical: https://veragent.store/agents/agent-req-78d63cb6