Skip to main content
Glama
@yawlabs/electron-mcp

@yawlabs/electron-mcp

Official
by YawLabs

electron_configure_deep_linking

Read-onlyIdempotent

Generates complete custom protocol and deep linking setup for Electron apps, including protocol registration, URL route handling, platform-specific config, and electron-builder or forge integration.

Instructions

Generate complete custom protocol / deep linking setup for Electron. Produces protocol registration, URL handling in both single-instance and multi-instance modes, platform-specific configuration (macOS Info.plist, Windows registry, Linux .desktop), and electron-builder/forge config.

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": {
      "protocol": "<protocol>"
    },
    "name": "electron_configure_deep_linking"
  }
}

Input Schema

NameRequiredDescriptionDefault
routesNoRoutes to handle within the protocol
protocolYesCustom protocol scheme, e.g. 'myapp' (will handle myapp:// URLs)
singleInstanceNoEnforce single instance -- new URLs focus the existing window (default true)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.7.2
    • removedInput schema / additionalProperties
      Removed value: -false
    • removedInput schema / properties / routes / items / additionalProperties
      Removed value: -false
  2. Changed1 schema field changedv1.2.15
    • addedInput schema / properties / protocol / pattern
      Added value: +"^[a-zA-Z][a-zA-Z0-9+.-]*(?::\\/\\/.*)?$"
  3. First observedv1.2.13

TDQS

A3.8/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description usefully adds the platform-by-platform scope of what gets produced, but it never resolves whether the tool writes files to disk or returns code/config to be applied, which is the key operational unknown for a "generate" tool under a readOnly annotation.

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

Conciseness5/5

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

One dense sentence, front-loaded with the verb and resource, followed by a parallel enumeration of delivered artifacts. No filler, no restatement of the name, nothing that could be cut without losing information.

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?

With only three fully described parameters, no output schema, and complete annotations, the definition is close to sufficient. The enumeration of produced artifacts effectively substitutes for a return-value description, though a note on output form (files vs. returned code) and on any ordering prerequisites would make it fully self-contained.

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%, so protocol, singleInstance, and nested routes are fully documented in the schema and the baseline applies. The description only glancingly reinforces the singleInstance behavior ("single-instance and multi-instance modes") and adds nothing about the protocol or routes semantics beyond what the schema states.

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

Purpose5/5

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

Names a specific verb and resource ("Generate complete custom protocol / deep linking setup for Electron") and then enumerates the concrete artifacts: protocol registration, URL handling for single/multi-instance, macOS Info.plist, Windows registry, Linux .desktop, and builder/forge config. That output list is distinctive enough to separate it from configure_csp, configure_fuses, and configure_auto_update without opening sibling schemas.

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

Usage Guidelines3/5

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

Usage is only implied: an agent can infer you call this when you need deep linking wired up. There is no explicit when-to-use trigger, no prerequisite statement, and no note on how it relates to sibling configure_* tools or to later steps like generate_preload_bridge that would consume the URL events.

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