AI agents call feishu_wiki_node_get to retrieve information from Lark Cli without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves Wiki node details without creating, modifying, deleting, or executing operations. It is a read-only query operation with no side effects. Severity is low because it only fetches data the user would normally be able to access through Feishu/Lark.
From the tool's definition Tool name contains 'get' and description states '读取一个 Wiki 节点详情' (retrieve Wiki node details). Accepts identifiers (Lark URL, node_token, obj_token) as parameters and retrieves information without modification.
Attacks that exploit this kind of access
读取一个 Wiki 节点详情（支持传 Lark URL / node_token / obj_token）. It is categorised as a Read tool in the Lark Cli MCP Server, which means it retrieves data without modifying state.
Register the Lark Cli MCP server in PolicyLayer and add a rule for feishu_wiki_node_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 Lark Cli. Nothing to install.
feishu_wiki_node_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 feishu_wiki_node_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 feishu_wiki_node_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.
feishu_wiki_node_get is provided by the Lark Cli MCP server (yoreland/lark-cli-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 →