$ loading_
Collaboratively plan tasks with AI using a local kanban and dependency graph.
This MCP tool is described as managing a shared local kanban and dependency graph, with no stated secrets or remote endpoints, so the overall risk appears relatively low. However, it is flagged as executing code and comes from a third-party registry with very low adoption and unknown maintenance status, so least-privilege use is still recommended.
The materials explicitly state that no keys or environment variables are required, and there is no indication of API tokens, account passwords, or other sensitive credentials being requested; based on the provided facts, credential exposure appears minimal.
No remote endpoints are declared in the materials, and the description says data is 'all stored locally'; there is no factual indication that user data is sent to external services.
The objective checks flag this tool as executes-code, indicating normal MCP capability to run code/processes locally. The materials do not define the exact system-capability boundaries, so it warrants standard caution for local code execution, but this alone is not enough to rate it as high risk.
The description indicates that it stores the shared kanban and dependency graph locally, so it at least involves local data read/write access. The materials do not specify directory scope or whether it is limited to its own workspace, so it should be treated as standard local data access and constrained accordingly.
Positive factors include open-source code and an MIT license, which improve auditability versus closed-source tools. However, it comes from a third-party registry, the GitHub repository has 0 stars, maintenance is unknown, and the README is absent, so supply-chain confidence is limited and merits caution, though no specific red flag is evident.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "roadmap-skill" yet — see the docs or source repo.
Create a task roadmap for our 2.0 release with six stages: requirement freeze, development, testing, documentation, canary rollout, and production launch. Organize tasks in a kanban board and show key dependencies and milestones.
An actionable release kanban with phases, task cards, dependencies, and milestone notes.
Plan a website redesign project across product, design, and engineering teams. Create a shared kanban listing each team’s tasks, suggested owners, predecessor and successor dependencies, and possible blockers.
A cross-functional project board that clearly shows responsibilities, task order, and potential risks.
Organize this project backlog: fix login bug, add monitoring alerts, optimize database queries, update API documentation, and add regression tests. Prioritize the items, place them on a kanban board, and define any necessary dependencies.
A prioritized backlog board with task sequencing and execution recommendations.
Semantically search a local skill library and load only relevant skills on demand.
Create, refine, validate, and restructure AgentSkills and SKILL.md files.
Match tasks to skills, track performance, detect gaps, and discover new skills.
Manage Linear issues, projects, and team workflows with AI assistance
Generate reusable AI agent skills and draft configs from website documentation.
Lets agents manage issues on a local-first Kanban board from Claude Code.