This record as markdown: /tools/nasbridge/app-upgrade.md
What app_upgrade does on Nasbridge
AI agents invoke app_upgrade to trigger actions in Nasbridge. 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.
Why app_upgrade is rated High
Upgrading an application triggers an external operation that modifies the running state of the app (replacing binaries, configs, potentially restarting services). It is not a simple write/read, but an active execution that changes system state. Misuse could cause service disruption or incompatibility, hence high severity.
From the tool's definition Upgrade an app to a newer version
Attacks that exploit this kind of access
The rule that runs app_upgrade safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Nasbridge, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For app_upgrade, this is the rule to start with:
app_upgrade stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Nasbridge, apply this rule, and every app_upgrade call is checked against it from then on.
Questions about app_upgrade
Upgrade an app to a newer version. It is categorised as a Execute tool in the Nasbridge MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Nasbridge MCP server in PolicyLayer and add a rule for app_upgrade: 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 Nasbridge. Nothing to install.
app_upgrade 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 app_upgrade 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 app_upgrade. 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.
app_upgrade is provided by the Nasbridge MCP server (maverick0628/nasbridge). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Nasbridge, and thousands of servers like it.
Across the catalogue