ToolTrust
D59/100
samihalawa

samihalawa-visual-ui-debug-agent-mcp

mcp1.0.1

@samihalawa

VUDA is an autonomous debugging agent that empowers AI models to visually analyze, test, and debug web

By samihalawa | 146 findings | Scanned 5/30/2026 | tooltrust-scanner/v0.3.13 | 78

38 High33 Medium40 Low35 Info

Risk Summary

Block in Production

Excessive Permissions + Dep Visibility risk is significant. Avoid using this in production agents.

Potential impact: The agent may gain overly broad access to files, network, databases, or execution capabilities.

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

{
  "mcpServers": {
    "samihalawa-visual-ui-debug-agent-mcp": {
      "disabled": true
    }
  }
}

Security Findings (146)

  • HighAS-002

    ⚠️Excessive Permissions ×33

    tool declares network permission

    axint.statusaxint.upgradeaxint.doctoraxint.xcode.guardaxint.session.startaxint.featureaxint.project.packaxint.project.syncVersionaxint.context.memoryaxint.context.docsaxint.registry.searchaxint.workflow.checkaxint.scaffoldaxint.compileaxint.validateaxint.fix-packetaxint.agent.installaxint.agent.adviceaxint.agent.claimaxint.agent.releaseaxint.run.statusaxint.run.cancelaxint.tokens.ingestaxint.schema.compileaxint.swift.validateaxint.swift.fixaxint.templates.listaxint.templates.get

    tool declares exec permission

    axint.featureaxint.suggestaxint.scaffoldaxint.runaxint.schema.compile

    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 ×5

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

    axint.xcode.guardaxint.xcode.writeaxint.workflow.check

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

    axint.featureaxint.schema.compile

    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.

  • MediumAS-002

    ⚠️Excessive Permissions ×33

    tool declares fs permission

    axint.statusaxint.doctoraxint.xcode.guardaxint.xcode.writeaxint.session.startaxint.featureaxint.project.packaxint.project.indexaxint.project.syncVersionaxint.context.memoryaxint.context.docsaxint.workflow.checkaxint.scaffoldaxint.compileaxint.validateaxint.fix-packetaxint.cloud.checkaxint.repairaxint.feedback.createaxint.agent.installaxint.agent.adviceaxint.agent.claimaxint.agent.releaseaxint.runaxint.run.statusaxint.tokens.ingestaxint.schema.compileaxint.swift.validateaxint.swift.fixaxint.templates.listaxint.templates.get

    tool declares db permission

    axint.registry.searchaxint.templates.list

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

  • LowAS-011

    ℹ️Missing Rate-Limit / Timeout ×29

    tool performs network or execution operations but declares no rate-limit, timeout, or retry configuration

    axint.statusaxint.upgradeaxint.doctoraxint.xcode.guardaxint.session.startaxint.featureaxint.project.packaxint.project.syncVersionaxint.context.memoryaxint.context.docsaxint.suggestaxint.registry.searchaxint.workflow.checkaxint.scaffoldaxint.compileaxint.validateaxint.fix-packetaxint.agent.installaxint.agent.adviceaxint.agent.claimaxint.agent.releaseaxint.run.statusaxint.run.cancelaxint.tokens.ingestaxint.schema.compileaxint.swift.validateaxint.swift.fixaxint.templates.listaxint.templates.get

    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.

  • LowAS-002

    ⚠️Excessive Permissions ×11

    input schema exposes 14 properties (threshold: 10)

    axint.xcode.guard

    input schema exposes 12 properties (threshold: 10)

    axint.xcode.write

    input schema exposes 11 properties (threshold: 10)

    axint.feature

    tool declares http permission

    axint.context.memoryaxint.schema.compile

    input schema exposes 23 properties (threshold: 10)

    axint.workflow.check

    input schema exposes 15 properties (threshold: 10)

    axint.cloud.check

    input schema exposes 17 properties (threshold: 10)

    axint.repair

    input schema exposes 16 properties (threshold: 10)

    axint.feedback.create

    input schema exposes 27 properties (threshold: 10)

    axint.run

    input schema exposes 18 properties (threshold: 10)

    axint.schema.compile

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

  • InfoAS-014

    ℹ️Dependency Inventory Unavailable ×35

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

    axint.statusaxint.upgradeaxint.doctoraxint.xcode.guardaxint.xcode.writeaxint.session.startaxint.featureaxint.project.packaxint.project.indexaxint.project.syncVersionaxint.context.memoryaxint.context.docsaxint.suggestaxint.registry.searchaxint.workflow.checkaxint.scaffoldaxint.compileaxint.validateaxint.fix-packetaxint.cloud.checkaxint.repairaxint.feedback.createaxint.agent.installaxint.agent.adviceaxint.agent.claimaxint.agent.releaseaxint.runaxint.run.statusaxint.run.cancelaxint.tokens.ingestaxint.schema.compileaxint.swift.validateaxint.swift.fixaxint.templates.listaxint.templates.get

    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 samihalawa-visual-ui-debug-agent-mcp"

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)