Get a dependency planning view by project ID and view ID. Returns Agent-friendly task snapshots by default; set verbose=true for raw node and edge data.
AI agents call get_dependency_view to retrieve information from Roadmap Skill without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only query of existing project data (dependency views). It retrieves and returns information about tasks, nodes, and edges without creating, modifying, or deleting any data. The verbose parameter is a presentation option, not a side effect. This is a straightforward data retrieval operation with no blast radius if misused by an AI agent.
From the tool's definition Tool description explicitly states 'Get a dependency planning view' — a retrieval operation that returns task snapshots or raw data without modifying state.
Documented attack patterns abuse exactly the kind of access get_dependency_view gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Roadmap Skill, and nothing reaches the server without passing your rules. This is the rule we recommend for get_dependency_view:
{
"version": "1",
"default": "deny",
"tools": {
"get_dependency_view": {}
}
}get_dependency_view is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get a dependency planning view by project ID and view ID. Returns Agent-friendly task snapshots by default; set verbose=true for raw node and edge data. It is categorised as a Read tool in the Roadmap Skill MCP Server, which means it retrieves data without modifying state.
Register the Roadmap Skill MCP server in PolicyLayer and add a rule for get_dependency_view: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Roadmap Skill. Nothing to install.
get_dependency_view is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_dependency_view rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for get_dependency_view. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
get_dependency_view is provided by the Roadmap Skill MCP server (shiquda/roadmap-skill). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 32 Roadmap Skill tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
32 Roadmap Skill tools catalogued and risk-classified — across an index of 42,500+ MCP servers.