AI agents use push_msg to create or update resources in SiYuan MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your SiYuan MCP Server environment.
Pushing a message creates or sends data (a message) but does not execute arbitrary code, delete data irreversibly, or move money. It's a standard write operation with limited blast radius—worst case is unwanted messages being sent, which is reversible or low-impact.
From the tool's definition Tool name 'push_msg' and description '推送消息' (push message) indicate sending/posting a message. This is a write operation that creates new message data.
Documented attack patterns abuse exactly the kind of access push_msg gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and SiYuan MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for push_msg:
{
"version": "1",
"default": "deny",
"tools": {
"push_msg": {
"limits": [
{
"counter": "push_msg_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}push_msg 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.
推送消息. It is categorised as a Write tool in the SiYuan MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the SiYuan MCP Server MCP server in PolicyLayer and add a rule for push_msg: 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 SiYuan MCP Server. Nothing to install.
push_msg 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 push_msg 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 push_msg. 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.
push_msg is provided by the SiYuan MCP Server MCP server (xgq18237/siyuan_mcp_server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 52 SiYuan MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
52 SiYuan MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.