Get a specific item by ID from craft.io (e.g., UPS-1234)
AI agents call craft_get_item to retrieve information from Craft MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves a single item by its ID without modifying, deleting, or executing any operations. It is a straightforward read operation with no side effects. Low severity reflects minimal blast radius—an agent querying items cannot cause harm to systems or data integrity.
From the tool's definition Tool name 'craft_get_item' and description 'Get a specific item by ID' indicate retrieval of data. Server description explicitly states 'read access to craft.io workspaces and items' with capability to 'retrieve specific items'.
Attacks that exploit this kind of access
Get a specific item by ID from craft.io (e.g., UPS-1234). It is categorised as a Read tool in the Craft MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Craft MCP Server MCP server in PolicyLayer and add a rule for craft_get_item: 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 Craft MCP Server. Nothing to install.
craft_get_item 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 craft_get_item 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 craft_get_item. 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.
craft_get_item is provided by the Craft MCP Server MCP server (upstackjade/craft_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →