AI agents use publish_item to create or update resources in FishClaw MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your FishClaw MCP environment.
The tool publishes items to the Xianyu marketplace, creating new listings. This is a Write operation (creates data) rather than Destructive (listings can typically be delisted/unpublished). Severity is high because an AI agent could publish large numbers of items, spam listings, or publish inappropriate content to a live marketplace, causing reputational and operational damage.
From the tool's definition Tool name 'publish_item' and description '点击发布按钮完成商品发布' (click the publish button to complete product publication) indicate the tool creates/publishes new marketplace listings. This is a reversible write operation that modifies marketplace state.
Documented attack patterns abuse exactly the kind of access publish_item gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and FishClaw MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for publish_item:
{
"version": "1",
"default": "deny",
"tools": {
"publish_item": {
"limits": [
{
"counter": "publish_item_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}publish_item 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.
点击发布按钮完成商品发布。. It is categorised as a Write tool in the FishClaw MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the FishClaw MCP server in PolicyLayer and add a rule for publish_item: 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 FishClaw MCP. Nothing to install.
publish_item 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_item 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_item. 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_item is provided by the FishClaw MCP server (tnoobt/fishclaw_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from FishClaw MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
12 FishClaw MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.