发布草稿(需要相应权限)
AI agents use publish_draft to create or update resources in WeChat Official Account MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your WeChat Official Account MCP Server environment.
Publishing a draft creates/modifies public-facing content on a WeChat Official Account that reaches users, making it a Write operation. It is not Destructive (the draft itself remains and can be re-published), not Execute (no code/commands), not Financial (no direct money movement).
From the tool's definition Tool name 'publish_draft' and Chinese description '发布草稿(需要相应权限)' (publish draft with corresponding permissions) indicate this tool publishes previously created draft content to a WeChat Official Account.
Attacks that exploit this kind of access
发布草稿(需要相应权限). It is categorised as a Write tool in the WeChat Official Account MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the WeChat Official Account MCP Server MCP server in PolicyLayer and add a rule for publish_draft: 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 WeChat Official Account MCP Server. Nothing to install.
publish_draft 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 publish_draft 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 publish_draft. 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.
publish_draft is provided by the WeChat Official Account MCP Server MCP server (jungley8/mcp4agent). 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 →