assert · Web Bridge MCP: Risk & Policy

WHAT IT DOES

What assert does on Web Bridge

AI agents use assert to create or update resources in Web Bridge — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Web Bridge environment.

PARAMETERS

Parameter	Type	Required	Description
`image`	object	—	Reference image URL/path. Repeat --image for multiple images.
`prompt`	string	Yes	Natural language assertion to verify, e.g. "there is a login button visible"
`message`	string	—	Custom error message to throw when the assertion fails, e.g. "the login button should be visible".
`web.url`	string	—	URL to open in new tab (omit to use current page)
`imageName`	object	—	Reference image name. Repeat --image-name; must align with --image order.
`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.
`convertHttpImage2Base64`	boolean \| string	—	If true, convert http(s) image URLs to base64 before sending to the model.
`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.

WHY IT NEEDS A POLICY

Why assert needs a policy

An AI agent can call assert faster than any human can review — one bad instruction and it creates or modifies resources in Web Bridge by the hundred, each call as confident as the last.

Risk signalsAccepts URL/endpoint input (web.url) · High parameter count (10 properties)

Attacks that exploit this kind of access

Questions about assert

What does the assert tool do? +

Assert a natural language statement against the current page/screen. It is categorised as a Write tool in the Web Bridge MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does assert accept? +

assert accepts 10 parameters: image, prompt, message, web.url, imageName, web.aiActContext, web.waitAfterAction, convertHttpImage2Base64, web.replanningCycleLimit, web.screenshotShrinkFactor. Required: prompt. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on assert? +

Register the Web Bridge MCP server in PolicyLayer and add a rule for assert: 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.

What risk level is assert? +

assert is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit assert? +

Yes. Add a rate_limit block to the assert 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.

How do I block assert completely? +

Set action: deny in the PolicyLayer policy for assert. 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.

What MCP server provides assert? +

assert 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.