// SCAN REPORT

Roadmap Skill

32 tools. 21 can modify or destroy data without limits.

6 destructive tools with no built-in limits. Policy required.

Last updated: 11 Jun 2026

21 can modify or destroy data

11 read-only

32 tools total

Community server · catalogue entry verified 11/06/2026

How to control Roadmap Skill ↓

TOOL MAP

Read (11) Write / Execute (15) Destructive / Financial (6)

MOST DANGEROUS TOOLS

Critical Risk

Destructive · High delete_dependency_view This tool performs an irreversible deletion operation on a dependency planning view. Destructive · High delete_project This tool permanently removes a project and all associated data (tasks, dependencies, metadata) with no undo mechanism mentioned. Destructive · Medium delete_tag The tool performs an irreversible deletion of a tag. Destructive · High delete_task This tool permanently removes task data from the system with no undo mechanism indicated.

21 of Roadmap Skill's 32 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

HOW TO CONTROL ROADMAP SKILL

PolicyLayer is an MCP gateway — it sits between your AI agents and Roadmap Skill, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "delete_dependency_view": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "add_dependency_view_edge": {
    "limits": [
      {
        "counter": "add_dependency_view_edge_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "analyze_dependency_view": {
    "limits": [
      {
        "counter": "analyze_dependency_view_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Roadmap Skill — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON ROADMAP SKILL →

Free to start. No card required.

ALL 32 ROADMAP SKILL TOOLS

DESTRUCTIVE 6 tools

Destructive delete_dependency_view Delete a dependency planning view by project ID and view ID Destructive delete_project Delete a project by ID Destructive delete_tag Delete a tag by project ID and tag ID Destructive delete_task Delete a task by project ID and task ID Destructive remove_dependency_view_edge Remove a dependency edge from a dependency planning view. Returns summary plus changed ids by default; set ver Destructive remove_task_from_dependency_view Remove a task node from a dependency planning view. Connected edges are removed too. Returns summary plus chan

WRITE 15 tools

Write add_dependency_view_edge Create a dependency edge between two tasks already present in a dependency planning view. Returns summary plus Write add_task_to_dependency_view Add an existing task into a dependency planning view. Returns summary plus changed ids by default; set verbose Write apply_template Create a new project from a template Write batch_update_dependency_view_nodes Update multiple task node layouts or notes inside a dependency planning view. Returns summary plus changed ids Write batch_update_tasks Update multiple tasks at once. tags must be existing tag IDs from the same project. Returns summaries by defau Write create_dependency_view Create a dependency planning view inside a project. Returns summary by default; set verbose=true for full data Write create_project Create a new project roadmap. Returns summary by default; set verbose=true for full data. Write create_tag Create a new tag in a project. If color is omitted, it is generated deterministically from tag name. Write create_task Create a new task in a project. tags must be existing tag IDs from the same project. Returns summary by defaul Write update_dependency_view Update dependency planning view metadata. Returns summary by default; set verbose=true for full data. Write update_dependency_view_edge Update the direction of a dependency edge inside a dependency planning view. Returns summary plus changed ids Write update_dependency_view_node Update a task node layout or note inside a dependency planning view. Returns summary plus changed ids by defau Write update_project Update an existing project. Returns summary by default; set verbose=true for full data. Write update_tag Update an existing tag Write update_task Update an existing task. tags must be existing tag IDs from the same project. Returns summary by default; set

READ 11 tools

Read analyze_dependency_view Analyze a dependency planning view and return topological layers, ready tasks, blocked tasks, roots, leaves, a Read get_dependency_view Get a dependency planning view by project ID and view ID. Returns Agent-friendly task snapshots by default; se Read get_project Get a project by ID with all its data (tasks, tags, milestones). Tasks are returned as summaries by default; s Read get_task Get a specific task by project ID and task ID Read get_tasks_by_tag Get all tasks that have a specific tag Read get_template Get detailed information about a specific template Read list_dependency_views List dependency planning views in a project. Returns summaries by default; set includeTasks=true for Agent-fri Read list_projects List all projects. Summary mode includes current project tags for Agent reuse. Set verbose=true for full proje Read list_tasks List tasks with optional filters. By default, completed (done) tasks are excluded. Set includeCompleted=true t Read list_templates List all available project templates

RELATED SERVERS

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Can an AI agent delete data through the Roadmap Skill MCP server? +

Yes. The Roadmap Skill server exposes 6 destructive tools including delete_dependency_view, delete_project, delete_tag. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Roadmap Skill? +

The Roadmap Skill server has 15 write tools including add_dependency_view_edge, add_task_to_dependency_view, apply_template. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Roadmap Skill.

How many tools does the Roadmap Skill MCP server expose? +

32 tools across 3 categories: Destructive, Read, Write. 11 are read-only. 21 can modify, create, or delete data.

How do I enforce a policy on Roadmap Skill? +

Register the Roadmap Skill MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Roadmap Skill tool call.

Deterministic rules across all 32 Roadmap Skill tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON ROADMAP SKILL →

Free to start. No card required.

32 Roadmap Skill tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

Roadmap Skill

// TOOL MAP

// MOST DANGEROUS TOOLS

// HOW TO CONTROL ROADMAP SKILL

// ALL 32 ROADMAP SKILL TOOLS

// RELATED SERVERS

// FAQ