Installs a new ScriptButton into a specific module (Name, Script, Icon, Tooltip).
AI agents use deploy_script_button to create or update resources in PyNet Bridge — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your PyNet Bridge environment.
The tool creates/installs a new UI element (ScriptButton) in a module. This is a Write operation as it adds a new artifact to the system. While the button references a script, the act of deploying the button itself is a reversible write (there is a sibling 'delete_script_button' tool, confirming it can be undone).
From the tool's definition Installs a new ScriptButton into a specific module (Name, Script, Icon, Tooltip)
Attacks that exploit this kind of access
Installs a new ScriptButton into a specific module (Name, Script, Icon, Tooltip). It is categorised as a Write tool in the PyNet Bridge MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the PyNet Bridge MCP server in PolicyLayer and add a rule for deploy_script_button: 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 PyNet Bridge. Nothing to install.
deploy_script_button is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the deploy_script_button 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 deploy_script_button. 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.
deploy_script_button is provided by the PyNet Bridge MCP server (rafael-nunezdearenas/pynetbridge). 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 →