查询指定节点所需的已登录的cookie信息。
AI agents call fetch_node_cookie to retrieve information from ShowDoc 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 cookie information, which is a read operation with no data modification. However, the severity is elevated to 'medium' because cookies represent sensitive authentication credentials—if an agent misuses this capability, it could leak session tokens or authentication data that could be weaponized for unauthorized access, impersonation, or privilege escalation.
From the tool's definition Tool name 'fetch_node_cookie' and description '查询指定节点所需的已登录的cookie信息' (query specified node's required logged-in cookie information) indicates retrieval of sensitive authentication data without modification.
Attacks that exploit this kind of access
查询指定节点所需的已登录的cookie信息。. It is categorised as a Read tool in the ShowDoc MCP Server MCP Server, which means it retrieves data without modifying state.
Register the ShowDoc MCP Server MCP server in PolicyLayer and add a rule for fetch_node_cookie: 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 ShowDoc MCP Server. Nothing to install.
fetch_node_cookie 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 fetch_node_cookie 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 fetch_node_cookie. 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.
fetch_node_cookie is provided by the ShowDoc MCP Server MCP server (yfcyfc123234/showdoc_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 →