Execute a natural language action. The AI will plan and perform multi-step operations in a single invocation, useful for transient UI interactions (e.g., Spotlight, dropdown menus) that disappear between separate commands.
AI agents invoke act to trigger actions in Web Bridge. 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
prompt | string | Yes | Natural language description of the action to perform, e.g. "press Command+Space, type Safari, press Enter" |
web.url | string | — | URL to open in new tab (omit to use current page) |
deepThink | boolean | — | Plan this action with deep thinking (richer context and sub-goal decomposition). Helps with complex multi-step instructions at the cost of speed. Defaults to th |
deepLocate | boolean | — | Use deep locate for every element this action targets. Improves precision for small or ambiguous targets at the cost of speed. Defaults to the server --deep-loc |
web.aiActContext | string | — | Background knowledge passed to aiAct. Default: no extra context. |
web.waitAfterAction | number | — | Wait time in milliseconds after each action execution. Default: 300ms. |
web.replanningCycleLimit | integer | — | Maximum number of replanning cycles for aiAct. Default: model adapter default. |
web.screenshotShrinkFactor | number | — | Screenshot shrink factor before sending images to AI. Default: 1; high values may reduce recognition quality, especially on mobile. |
Parameters from the server's own tool schema.
This tool triggers execution of AI-planned multi-step operations based on natural language input. While presented as a web automation tool for UI interactions, the ability to 'plan and perform' arbitrary operations with user-supplied instructions constitutes code execution.
From the tool's definition Tool description states it will 'Execute a natural language action' and 'perform multi-step operations', with the ability to interact with UI elements (Spotlight, dropdowns, etc.).
Risk signalsAccepts URL/endpoint input (web.url)
Attacks that exploit this kind of access
Execute a natural language action. The AI will plan and perform multi-step operations in a single invocation, useful for transient UI interactions (e.g., Spotlight, dropdown menus) that disappear between separate commands. It is categorised as a Execute tool in the Web Bridge MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
act accepts 8 parameters: prompt, web.url, deepThink, deepLocate, web.aiActContext, web.waitAfterAction, web.replanningCycleLimit, web.screenshotShrinkFactor. Required: prompt. The full parameter table on this page comes from the server's own tool schema.
Register the Web Bridge MCP server in PolicyLayer and add a rule for act: 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 Web Bridge. Nothing to install.
act 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 act 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 act. 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.
act is provided by the Web Bridge MCP server (@midscene/web-bridge-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →