AI agents call get_work_item_detail to retrieve information from MCP Feishu Project Manager without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves details about a work item from a Feishu project management system. Retrieval operations that query or fetch data without modifying state are classified as Read. The absence of a detailed description slightly lowers confidence, but the naming convention and sibling tools strongly suggest it performs only data retrieval with no side effects.
From the tool's definition Tool name 'get_work_item_detail' follows the 'get_*' naming convention, consistent with sibling tools like 'get_flow_roles', 'get_view_detail', and 'get_view_list'. Description is empty, but the pattern and context indicate data retrieval.
Documented attack patterns abuse exactly the kind of access get_work_item_detail gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Feishu Project Manager, and nothing reaches the server without passing your rules. This is the rule we recommend for get_work_item_detail:
{
"version": "1",
"default": "deny",
"tools": {
"get_work_item_detail": {}
}
}get_work_item_detail 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_work_item_detail. It is categorised as a Read tool in the MCP Feishu Project Manager MCP Server, which means it retrieves data without modifying state.
Register the MCP Feishu Project Manager MCP server in PolicyLayer and add a rule for get_work_item_detail: 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 Feishu Project Manager. Nothing to install.
get_work_item_detail 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_work_item_detail 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_work_item_detail. 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_work_item_detail is provided by the MCP Feishu Project Manager MCP server (roland0511/mcp-feishu-proj). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Feishu Project Manager, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
6 MCP Feishu Project Manager tools catalogued and risk-classified — across an index of 43,000+ MCP servers.