AI agents use set_wecom_cookie to create or update resources in Wecom Doc — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Wecom Doc environment.
This tool creates/modifies configuration data (storing cookies to a local file) rather than just reading it, making it a Write operation. Severity is high because storing authentication tokens introduces credential exposure risks: misconfigured access, token interception, or unauthorized credential reuse if the config file is compromised.
From the tool's definition Tool name and description: 'set_wecom_cookie' — '保存企业微信 Cookie 到本地配置文件,后续请求自动使用' (save Enterprise WeChat Cookie to local config file, subsequent requests automatically use it). The tool persists authentication credentials to local storage.
Attacks that exploit this kind of access
保存企业微信 Cookie 到本地配置文件,后续请求自动使用。. It is categorised as a Write tool in the Wecom Doc MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Wecom Doc MCP server in PolicyLayer and add a rule for set_wecom_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 Wecom Doc. Nothing to install.
set_wecom_cookie is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the set_wecom_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 set_wecom_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.
set_wecom_cookie is provided by the Wecom Doc MCP server (tiansiyu-tj/wecom-doc-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 →