Retrieves complete details of a specific task including all metadata, content sections, and relationships. Essential for understanding task requirements, current status, and context before making updates. For subtasks within parent tasks, provide parent_id to ensure correct resolution. Returns wo...
AI agents call task_get to retrieve information from Scopecraft Command without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a retrieval operation on task metadata and content without modifying, deleting, or executing any operations. It is purely informational, similar to a GET request in REST APIs. The low blast radius reflects that misuse would only expose information, not cause system changes or data loss.
From the tool's definition Tool name 'task_get' and description explicitly states it 'Retrieves complete details' and 'Returns workflow location, task structure, and all available content.' The verb 'retrieves' and absence of any modification, deletion, or execution language confirm…
Documented attack patterns abuse exactly the kind of access task_get gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Scopecraft Command, and nothing reaches the server without passing your rules. This is the rule we recommend for task_get:
{
"version": "1",
"default": "deny",
"tools": {
"task_get": {}
}
}task_get 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.
Retrieves complete details of a specific task including all metadata, content sections, and relationships. Essential for understanding task requirements, current status, and context before making updates. For subtasks within parent tasks, provide parent_id to ensure correct resolution. Returns workflow location, task structure, and all available content. Use this when you need full information about a task including its instruction, tasks checklist, deliverable, and log sections. It is categorised as a Read tool in the Scopecraft Command MCP Server, which means it retrieves data without modifying state.
Register the Scopecraft Command MCP server in PolicyLayer and add a rule for task_get: 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 Scopecraft Command. Nothing to install.
task_get 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 task_get 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 task_get. 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.
task_get is provided by the Scopecraft Command MCP server (scopecraft/command). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 18 Scopecraft Command tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
18 Scopecraft Command tools catalogued and risk-classified — across an index of 42,500+ MCP servers.