Skip to main content
Glama
Sign In

Local MCP

by com.local-mcp
OverviewDiscussionsAdmin

Install LMCP

setup_install
Read-only

Returns a personalized LMCP install link and setup steps (~30 sec to install). LMCP is a free Mac and Windows app that gives access to Mail/Calendar/Contacts/Notes/Reminders on Mac, Outlook/Teams/OneDrive/Office on Windows, and 100+ tools on the user's machine (data stays local). A user would invoke this to install LMCP or reconnect it. Pass os ("macos" or "windows" for real install steps; linux/ios/android go to a waitlist). Optional: step, issue.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "os": "<os>"
    },
    "name": "setup_install"
  }
}

Input Schema

NameRequiredDescriptionDefault
osYesmacos | windows | linux | ios | android. Cloud connectors must pass os (or server asks). Desktop terminal clients may omit → macOS. macOS and Windows both get real install steps. Linux/mobile → waitlist (not supported yet).
stepNoIf stuck: connector | install | connecting_stuck | server_down.
issueNoOptional tag: gatekeeper_error, dot_not_green, install_failed, etc.

Output Schema

NameRequiredDescriptionDefault
osNoTarget operating system the instructions are for, when known.
instructionsYesFull human-readable, step-by-step install/setup text.
install_commandNoNot sent any more (#965): there is no one-line install; the steps are in `instructions`.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / properties / install_command / description
      Previous value: -"One-line terminal command to install LMCP, when applicable to this OS/step."New value: +"Not sent any more (#965): there is no one-line install; the steps are in `instructions`."
  2. Changed3 schema fields changed
    • removedInput schema / properties / email
      Removed value: -{
-  "description": "Optional. Helps Cloud Relay auto-connect after install.",
-  "type": "string"
-}
    • changedInput schema / properties / step / description
      Previous value: -"If stuck: connector | install | email | connecting_stuck | server_down."New value: +"If stuck: connector | install | connecting_stuck | server_down."
    • changedInput schema / properties / step / enum
      Previous value: -[
-  "connector",
-  "install",
-  "email",
-  "connecting_stuck",
-  "server_down"
-]New value: +[
+  "connector",
+  "install",
+  "connecting_stuck",
+  "server_down"
+]
  3. Changed1 schema field changed
    • changedInput schema / properties / os / description
      Previous value: -"macos | windows | linux | ios | android. Cloud connectors must pass os (or server asks). Desktop terminal clients may omit → macOS. Windows/Linux/mobile → waitlist (macOS-only today)."New value: +"macos | windows | linux | ios | android. Cloud connectors must pass os (or server asks). Desktop terminal clients may omit → macOS. macOS and Windows both get real install steps. Linux/mobile → waitlist (not supported yet)."
  4. First observed

TDQS

A3.9/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the description is not required to establish that this is a safe read. It adds real context beyond them anyway: the expected ~30 sec install time, that data stays local, and which platforms are unsupported. It omits return-value detail, but an output schema exists to cover that.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the return value first, followed by the platform scope and invocation guidance. The enumeration of Mail/Calendar/Contacts/Notes and Outlook/Teams/OneDrive/Office is partly marketing padding that does not help an agent decide or parameterize the call.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

All three parameters are documented in the schema, an output schema covers the returned link and steps, and the description supplies the platform-support boundaries that the enum alone conveys in compressed form. It is complete for a low-risk read tool; only sibling routing is left implicit.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the os enum description already explains macOS/Windows vs waitlist platforms and the terminal-client default. The description's os note largely restates the schema, and its 'Optional: step, issue' line names the parameters without explaining when to set them. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: it 'Returns a personalized LMCP install link and setup steps'. It defines what LMCP is and what 'a user would invoke this to install LMCP or reconnect it.' It does not explicitly distinguish itself from close siblings such as lmcp_install_upgrade, lmcp_doctor, or configure_clients.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description names the trigger conditions (install or reconnect) and states a clear platform boundary: linux/ios/android go to a waitlist instead of getting real install steps. It gives no explicit when-not guidance and never names an alternative tool (for example lmcp_doctor) for troubleshooting cases.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Local MCP toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources