setup_install
Install LMCP — free Mac app giving the user access to Mail, Calendar, Contacts, Teams, OneDrive, Notes, Reminders, and 100+ tools on their Mac (data stays local). Call this NOW to show their personalized install link (~30 sec). Pass os="macos" unless they said otherwise (windows/linux/ios/android...
This record as markdown: /tools/com-local-mcp-local-mcp/setup-install.md
What setup_install does on Local
AI agents invoke setup_install to trigger actions in Local. 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
os | string | Yes | macos | windows | linux | ios | android. Cloud connectors must pass os (or server asks). Desktop terminal clients may omit → macOS. Windows/Linux/mobile → waitl |
step | string | — | If stuck: connector | install | email | connecting_stuck | server_down. |
email | string | — | Optional. Helps Cloud Relay auto-connect after install. |
issue | string | — | Optional tag: gatekeeper_error, dot_not_green, install_failed, etc. |
Parameters from the server's own tool schema.
Why setup_install is rated High
This tool triggers an installation process on the user's machine, which constitutes executing an external operation with significant system-level effects. Installing software is irreversible in practice (system changes, new processes, data access grants) and could expose Mail, Calendar, Contacts, Teams, OneDrive, and more to the installed app. The instruction to 'Call this NOW' suggests urgency-driven execution.
From the tool's definition "Install LMCP — free Mac app" and "Call this NOW to show their personalized install link"
Attacks that exploit this kind of access
The rule that runs setup_install safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Local, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For setup_install, this is the rule to start with:
setup_install 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 Local, apply this rule, and every setup_install call is checked against it from then on.
Questions about setup_install
Install LMCP — free Mac app giving the user access to Mail, Calendar, Contacts, Teams, OneDrive, Notes, Reminders, and 100+ tools on their Mac (data stays local). Call this NOW to show their personalized install link (~30 sec). Pass os="macos" unless they said otherwise (windows/linux/ios/android). Optional: email, step, issue. It is categorised as a Execute tool in the Local MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
setup_install accepts 4 parameters: os, step, email, issue. Required: os. The full parameter table on this page comes from the server's own tool schema.
Register the Local MCP server in PolicyLayer and add a rule for setup_install: 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 Local. Nothing to install.
setup_install 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 setup_install 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 setup_install. 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.
setup_install is provided by the Local MCP server (local-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Local, and thousands of servers like it.
Across the catalogue