AI agents invoke fill_input to trigger actions in Mcp Playwright. 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.
Filling an input field is a browser automation action that triggers external operations on a web page. While it doesn't directly execute code or delete data, it performs an interactive operation in a browser that can have downstream effects (e.g., filling in form fields that submit data, credentials, or trigger other actions).
From the tool's definition Tool name 'fill_input' and description '填写输入框' (fill input field) indicating browser automation action that interacts with web page elements
Documented attack patterns abuse exactly the kind of access fill_input gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Playwright, and nothing reaches the server without passing your rules. This is the rule we recommend for fill_input:
{
"version": "1",
"default": "deny",
"tools": {
"fill_input": {
"limits": [
{
"counter": "fill_input_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}fill_input 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.
填写输入框. It is categorised as a Execute tool in the Mcp Playwright MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mcp Playwright MCP server in PolicyLayer and add a rule for fill_input: 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 Mcp Playwright. Nothing to install.
fill_input 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 fill_input 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 fill_input. 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.
fill_input is provided by the Mcp Playwright MCP server (ma-pony/mcp-playwright). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcp Playwright, 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 Mcp Playwright tools catalogued and risk-classified — across an index of 43,000+ MCP servers.