AI agents call fetch_wecom_doc to retrieve information from Wecom Doc without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and transforms existing document content for display purposes. There is no indication of create, modify, delete, or execute capabilities. The data flow is unidirectional (WeChat → Markdown output).
From the tool's definition Tool description states 'fetch_wecom_doc' and 'Allows AI assistants to fetch and read Enterprise WeChat documents' with conversion to Markdown. The verb 'fetch' and 'read' indicate data retrieval with no modification capability.
Attacks that exploit this kind of access
抓取企业微信文档内容并转为 Markdown。支持文档、表格、幻灯片等类型。. It is categorised as a Read tool in the Wecom Doc MCP Server, which means it retrieves data without modifying state.
Register the Wecom Doc MCP server in PolicyLayer and add a rule for fetch_wecom_doc: 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.
fetch_wecom_doc 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_wecom_doc 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_wecom_doc. 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_wecom_doc 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 →