Type the characters in the string that is passed.
AI agents invoke omniparser_write to trigger actions in Omniparser Autogui. 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.
This tool types arbitrary text into whatever UI element currently has focus on the user's desktop. It is an active GUI automation action with side effects that depend entirely on the string passed and the current focus context. It could type into documents, terminals, chat windows, web forms, etc.
From the tool's definition Type the characters in the string that is passed — automated GUI keyboard input on the live desktop
Documented attack patterns abuse exactly the kind of access omniparser_write gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Omniparser Autogui, and nothing reaches the server without passing your rules. This is the rule we recommend for omniparser_write:
{
"version": "1",
"default": "deny",
"tools": {
"omniparser_write": {
"limits": [
{
"counter": "omniparser_write_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}omniparser_write 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.
Type the characters in the string that is passed. It is categorised as a Execute tool in the Omniparser Autogui MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Omniparser Autogui MCP server in PolicyLayer and add a rule for omniparser_write: 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 Omniparser Autogui. Nothing to install.
omniparser_write 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 omniparser_write 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 omniparser_write. 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.
omniparser_write is provided by the Omniparser Autogui MCP server (non906/omniparser-autogui-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 9 Omniparser Autogui tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
9 Omniparser Autogui tools catalogued and risk-classified — across an index of 42,500+ MCP servers.