Install DroidCast on the specified device.
AI agents invoke install_droidcast to trigger actions in MSC MCP Server. 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.
Installing an application on a device is an external operation that modifies the device state by deploying new software. It is not a simple data write (it executes an ADB install command and runs installation logic on the device), and it is not purely destructive. The blast radius is medium: misuse could install unintended software on connected Android devices.
From the tool's definition 'Install DroidCast on the specified device' — installs software onto an Android device via ADB
Attacks that exploit this kind of access
Install DroidCast on the specified device. It is categorised as a Execute tool in the MSC MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MSC MCP Server MCP server in PolicyLayer and add a rule for install_droidcast: 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 MSC MCP Server. Nothing to install.
install_droidcast 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 install_droidcast 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 install_droidcast. 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.
install_droidcast is provided by the MSC MCP Server MCP server (nakanosanku/msc-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 →