ToolTrust
A2/100
Smithery

gantta-gantta-mcp

mcpsmithery

@Smithery

Turn conversations into project plans. Gantta connects your AI assistant to a full project management backend — plan projects, manage tasks, chase actions, and generate reports, all through natural language. ### What you can do - **Create project plans** — Describe your project in plain language and get a structured plan with milestones, dependencies, deadlines, and deliverables - **Break down tasks** — Automatically decompose projects into prioritised actions with owners, due dates, and status tracking - **Assign owners** — Allocate tasks to team members and track who is responsible for what across every project - **Chase actions automatically** — Follow up on overdue or pending actions with automatic owner notifications so nothing slips through the cracks - **Capture meeting transcriptions** — Log meeting notes, standups, or any conversation and extract structured action items automatically - **Generate reports and slide decks** — Produce project status reports, progress summaries, and presentation-ready slide decks directly from your project data - **Track timelines** — View project schedules, milestone progress, and dependency chains at a glance ### Who it's for Product managers, project leads, founders, and agency teams who run projects across multiple clients and want to manage everything from their AI assistant without switching tools. ### No account needed to start Try Gantta instantly — your AI assistant can create project plans right away. When you're ready to save your work, collaborate with your team, and unlock full reporting, claim your workspace at [gantta.co](https://www.gantta.co). ### Why Gantta over traditional PM tools Traditional project management tools require manual data entry, constant tab-switching, and rigid workflows. Gantta lets you manage projects the way you actually think — by talking. Your AI assistant becomes your project manager, handling the structure while you focus on the work. Built for teams who plan through conversation, not spreadsheets.

By Smithery | 43 findings | Scanned 6/24/2026 | tooltrust-scanner/v0.3.19

8 Low35 Info

Risk Summary

Safe With Normal Controls

Dep 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 (43)

  • LowAS-011

    ℹ️Missing Rate-Limit / Timeout ×8

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

    complete_onboardingcreate_actionupdate_actioncreate_projectprocess_meetingbot_join_meetingadd_assigneeshare_feedback

    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 ×26

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

    get_onboarding_statuscomplete_onboardingget_account_statusget_overdue_actionsget_project_summaryget_meeting_actionsget_blockerslist_actionslist_projectslist_meetingsget_meetingcreate_actionupdate_actiondelete_actioncreate_projectset_active_projectprocess_meetingbot_join_meetingbot_meeting_statusbot_stop_meetingadd_assigneelist_assigneessend_chaserclaim_accountget_plansshare_feedback

    Fix: Review and remediate the identified issue.

  • InfoAS-002

    ⚠️Excessive Permissions ×9

    declared capabilities: code/command execution

    complete_onboardingprocess_meetingadd_assignee

    declared capabilities: code/command execution, filesystem access

    create_actionupdate_actioncreate_project

    declared capabilities: filesystem access

    delete_action

    declared capabilities: network access

    bot_join_meeting

    declared capabilities: HTTP requests

    share_feedback

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