Type text into an input field by its ref ID. Uses human-like typing by default. Set clearFirst=true to click, select all, then type — required for React/Vue/Angular inputs where direct fill doesn
AI agents invoke pinchtab_type to trigger actions in Pinchtab. 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 browser interaction actions (typing, clicking, selecting) that produce external side effects depending on arguments. It's a browser automation action that could submit forms, enter credentials, or manipulate web application state — making it Execute category. Severity is medium because while it can't directly delete data, it can cause significant harm by entering malicious input into web forms.
From the tool's definition 'Type text into an input field by its ref ID. Uses human-like typing by default. Set clearFirst=true to click, select all, then type'
Attacks that exploit this kind of access
Type text into an input field by its ref ID. Uses human-like typing by default. Set clearFirst=true to click, select all, then type — required for React/Vue/Angular inputs where direct fill doesn. It is categorised as a Execute tool in the Pinchtab MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Pinchtab MCP server in PolicyLayer and add a rule for pinchtab_type: 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 Pinchtab. Nothing to install.
pinchtab_type 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 pinchtab_type 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 pinchtab_type. 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.
pinchtab_type is provided by the Pinchtab MCP server (maderwin/pinchtab-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 →