Perform click/type/fill/press/select interactions in browser session
AI agents invoke browser_interact to trigger actions in AutoDev MCP. 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 triggers real browser interactions (click, type, fill, press, select) whose effects depend entirely on arguments and context. These actions can submit forms, trigger purchases, modify application state, or perform any number of operations in a live browser session. Since the effects are argument-dependent and can be wide-ranging, Execute is the appropriate category.
From the tool's definition Perform click/type/fill/press/select interactions in browser session
Attacks that exploit this kind of access
Perform click/type/fill/press/select interactions in browser session. It is categorised as a Execute tool in the AutoDev MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the AutoDev MCP server in PolicyLayer and add a rule for browser_interact: 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 AutoDev MCP. Nothing to install.
browser_interact 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 browser_interact 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 browser_interact. 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.
browser_interact is provided by the AutoDev MCP server (rookiejefren/autocoding-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 →