ToolTrust
C25/100
its-dart

dart-mcp-server

mcp0.2.1

@its-dart

Dart AI Model Context Protocol (MCP) server

By its-dart | 33 findings | Scanned 6/3/2026 | tooltrust-scanner/v0.3.13 | 128

2 High9 Medium2 Low20 Info

Risk Summary

Needs Approval

Excessive Permissions plus Missing Description raises enough risk that this tool should not be auto-trusted.

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

Recommended action: Keep this tool behind manual approval and avoid unattended runs until the risky capabilities are narrowed or removed.

Suggested policy: keep this tool behind manual approval, do not allow unattended runs, and re-scan after narrowing risky permissions.

Security Findings (33)

  • HighAS-002

    ⚠️Excessive Permissions ×2

    tool declares exec permission

    dart-packagedart-run

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

  • MediumAS-002

    ⚠️Excessive Permissions ×9

    tool declares fs permission

    dart-analyzedart-compiledart-createdart-docdart-fixdart-formatdart-packagedart-rundart-test

    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 ×2

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

    dart-packagedart-run

    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-007

    ℹ️Missing Description or Schema ×10

    Tool 'dart-analyze' has no description - agents cannot reason about its purpose, and static analysis coverage is limited

    dart-analyze

    Tool 'dart-compile' has no description - agents cannot reason about its purpose, and static analysis coverage is limited

    dart-compile

    Tool 'dart-create' has no description - agents cannot reason about its purpose, and static analysis coverage is limited

    dart-create

    Tool 'dart-doc' has no description - agents cannot reason about its purpose, and static analysis coverage is limited

    dart-doc

    Tool 'dart-fix' has no description - agents cannot reason about its purpose, and static analysis coverage is limited

    dart-fix

    Tool 'dart-format' has no description - agents cannot reason about its purpose, and static analysis coverage is limited

    dart-format

    Tool 'dart-info' has no description - agents cannot reason about its purpose, and static analysis coverage is limited

    dart-info

    Tool 'dart-package' has no description - agents cannot reason about its purpose, and static analysis coverage is limited

    dart-package

    Tool 'dart-run' has no description - agents cannot reason about its purpose, and static analysis coverage is limited

    dart-run

    Tool 'dart-test' has no description - agents cannot reason about its purpose, and static analysis coverage is limited

    dart-test

    Fix: Review and remediate the identified issue.

  • InfoAS-014

    ℹ️Dependency Inventory Unavailable ×10

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

    dart-analyzedart-compiledart-createdart-docdart-fixdart-formatdart-infodart-packagedart-rundart-test

    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 dart-mcp-server"

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 C](https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-directory/main/docs/badges/grade-c.svg)](https://github.com/AgentSafe-AI/tooltrust-directory)