AI agents use wecom_send_markdown to create or update resources in autoMate — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your autoMate environment.
Sending messages to WeChat Work creates new data (messages) with side effects on external systems and user notifications. This is reversible communication (Write category), not destructive. Severity is medium due to potential for spam/harassment via messaging, though individual messages can be deleted.
From the tool's definition Tool name 'wecom_send_markdown' indicates sending/posting content to WeChat Work (WeChat Enterprise). The 'send' verb and integration context suggest message creation/transmission.
Documented attack patterns abuse exactly the kind of access wecom_send_markdown gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and autoMate, and nothing reaches the server without passing your rules. This is the rule we recommend for wecom_send_markdown:
{
"version": "1",
"default": "deny",
"tools": {
"wecom_send_markdown": {
"limits": [
{
"counter": "wecom_send_markdown_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}wecom_send_markdown stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
wecom_send_markdown. It is categorised as a Write tool in the autoMate MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the autoMate MCP server in PolicyLayer and add a rule for wecom_send_markdown: 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 autoMate. Nothing to install.
wecom_send_markdown 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 wecom_send_markdown 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 wecom_send_markdown. 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.
wecom_send_markdown is provided by the autoMate MCP server (yuruotong1/automate). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 128 autoMate tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
128 autoMate tools catalogued and risk-classified — across an index of 42,500+ MCP servers.