AI agents invoke douyin_navigate_to to trigger actions in Douyin Upload Mcp Skill. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Navigation via CDP is an Execute action because it triggers external browser operations and state changes that depend on supplied arguments. While restricted to douyin.com, a malicious agent could navigate to phishing pages, perform account hijacking, or trigger unintended platform actions.
From the tool's definition The tool description states it navigates to a specified Douyin page URL using Chrome DevTools Protocol. The name 'navigate_to' combined with the server's context of automating browser actions via CDP indicates this triggers browser navigation—an external…
Documented attack patterns abuse exactly the kind of access douyin_navigate_to gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Douyin Upload Mcp Skill, and nothing reaches the server without passing your rules. This is the rule we recommend for douyin_navigate_to:
{
"version": "1",
"default": "deny",
"tools": {
"douyin_navigate_to": {
"limits": [
{
"counter": "douyin_navigate_to_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}douyin_navigate_to stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
打开指定的抖音页面 URL。仅允许 douyin.com 域名. It is categorised as a Execute tool in the Douyin Upload Mcp Skill MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Douyin Upload Mcp Skill MCP server in PolicyLayer and add a rule for douyin_navigate_to: 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 Douyin Upload Mcp Skill. Nothing to install.
douyin_navigate_to is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the douyin_navigate_to 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 douyin_navigate_to. 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.
douyin_navigate_to is provided by the Douyin Upload Mcp Skill MCP server (wjz-p/douyin-upload-mcp-skill). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 8 Douyin Upload Mcp Skill tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
8 Douyin Upload Mcp Skill tools catalogued and risk-classified — across an index of 42,500+ MCP servers.