AI agents call get_items to retrieve information from Mcp Jama without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves project items without modifying, deleting, or executing any operations. It is a straightforward read/retrieval operation with no side effects. The low severity reflects minimal blast radius—fetching items poses no risk of data corruption or loss.
From the tool's definition Tool name 'get_items' and description indicating retrieval of project items list (maximum 50 items). The description describes pagination through start_at parameter for full retrieval, which is a read operation pattern.
Attacks that exploit this kind of access
プロジェクトのアイテム一覧を取得する（最大50件）。全件取得は start_at を増やして繰り返す。. It is categorised as a Read tool in the Mcp Jama MCP Server, which means it retrieves data without modifying state.
Register the Mcp Jama MCP server in PolicyLayer and add a rule for get_items: 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 Mcp Jama. Nothing to install.
get_items 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_items 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_items. 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_items is provided by the Mcp Jama MCP server (keisukeshima/mcp-jama). 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 →