Skip to main content
Glama

tauri_ipc_monitor

Idempotent

Monitor IPC calls between frontend and Rust backend in Tauri applications to capture invoke() calls and responses for debugging purposes.

Instructions

[Tauri Apps Only] Monitor Tauri IPC calls between frontend and Rust backend. Requires active tauri_driver_session. Captures invoke() calls and responses. This is Tauri-specific; for browser network monitoring, use Chrome DevTools MCP.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
actionYesAction to perform: start or stop IPC monitoring
appIdentifierNoApp port or bundle ID to target. Defaults to the only connected app or the default app if multiple are connected.

Implementation Reference

  • Core handler functions for 'tauri_ipc_monitor': manageIPCMonitoring dispatches start/stop actions, which send specific commands to the Tauri MCP Bridge plugin via executeIPCCommand to enable/disable IPC traffic monitoring.
    export const ManageIPCMonitoringSchema = z.object({
       action: z.enum([ 'start', 'stop' ]).describe('Action to perform: start or stop IPC monitoring'),
       appIdentifier: z.union([ z.string(), z.number() ]).optional().describe(
          'App port or bundle ID to target. Defaults to the only connected app or the default app if multiple are connected.'
       ),
    });
    
    // Keep individual schemas for backward compatibility if needed
    export const StartIPCMonitoringSchema = z.object({});
    export const StopIPCMonitoringSchema = z.object({});
    
    export async function manageIPCMonitoring(action: 'start' | 'stop', appIdentifier?: string | number): Promise<string> {
       if (action === 'start') {
          return startIPCMonitoring(appIdentifier);
       }
       return stopIPCMonitoring(appIdentifier);
    }
    
    export async function startIPCMonitoring(appIdentifier?: string | number): Promise<string> {
       try {
          const result = await executeIPCCommand({ command: 'plugin:mcp-bridge|start_ipc_monitor', appIdentifier });
    
          const parsed = JSON.parse(result);
    
          if (!parsed.success) {
             throw new Error(parsed.error || 'Unknown error');
          }
    
          return JSON.stringify(parsed.result);
       } catch(error: unknown) {
          const message = error instanceof Error ? error.message : String(error);
    
          throw new Error(`Failed to start IPC monitoring: ${message}`);
       }
    }
    
    export async function stopIPCMonitoring(appIdentifier?: string | number): Promise<string> {
       try {
          const result = await executeIPCCommand({ command: 'plugin:mcp-bridge|stop_ipc_monitor', appIdentifier });
    
          const parsed = JSON.parse(result);
    
          if (!parsed.success) {
             throw new Error(parsed.error || 'Unknown error');
          }
    
          return JSON.stringify(parsed.result);
       } catch(error: unknown) {
          const message = error instanceof Error ? error.message : String(error);
    
          throw new Error(`Failed to stop IPC monitoring: ${message}`);
       }
    }
  • Input validation schema for the 'tauri_ipc_monitor' tool, specifying 'action' ('start' or 'stop') and optional target app.
    export const ManageIPCMonitoringSchema = z.object({
       action: z.enum([ 'start', 'stop' ]).describe('Action to perform: start or stop IPC monitoring'),
       appIdentifier: z.union([ z.string(), z.number() ]).optional().describe(
          'App port or bundle ID to target. Defaults to the only connected app or the default app if multiple are connected.'
       ),
    });
  • Tool registration entry for 'tauri_ipc_monitor' in the central tools registry, linking schema, handler, description, and annotations.
    {
       name: 'tauri_ipc_monitor',
       description:
          '[Tauri Apps Only] Monitor Tauri IPC calls between frontend and Rust backend. ' +
          'Requires active tauri_driver_session. Captures invoke() calls and responses. ' +
          'This is Tauri-specific; for browser network monitoring, use Chrome DevTools MCP.',
       category: TOOL_CATEGORIES.IPC_PLUGIN,
       schema: ManageIPCMonitoringSchema,
       annotations: {
          title: 'Monitor Tauri IPC',
          readOnlyHint: false,
          destructiveHint: false,
          idempotentHint: true,
          openWorldHint: false,
       },
       handler: async (args) => {
          const parsed = ManageIPCMonitoringSchema.parse(args);
    
          return await manageIPCMonitoring(parsed.action, parsed.appIdentifier);
       },
    },
  • Shared helper function used by IPC monitoring handlers to execute arbitrary Tauri IPC commands via the WebSocket connection to the MCP Bridge plugin.
    export async function executeIPCCommand(options: {
       command: string;
       args?: unknown;
       appIdentifier?: string | number;
    }): Promise<string> {
       try {
          const { command, args = {}, appIdentifier } = options;
    
          // Ensure we have an active session and are connected
          const client = await ensureSessionAndConnect(appIdentifier);
    
          // Send IPC command via WebSocket to the mcp-bridge plugin
          const response = await client.sendCommand({
             command: 'invoke_tauri',
             args: { command, args },
          });
    
          if (!response.success) {
             return JSON.stringify({ success: false, error: response.error || 'Unknown error' });
          }
    
          return JSON.stringify({ success: true, result: response.data });
       } catch(error: unknown) {
          const message = error instanceof Error ? error.message : String(error);
    
          return JSON.stringify({ success: false, error: message });
       }
    }
Behavior4/5

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

The description adds valuable behavioral context beyond annotations: it specifies the prerequisite ('Requires active tauri_driver_session') and what gets captured ('Captures invoke() calls and responses'), which are not covered by annotations. Annotations provide safety hints (readOnlyHint: false, destructiveHint: false, idempotentHint: true), but the description complements this with operational details. No contradiction with annotations exists.

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?

The description is front-loaded with key information in three concise sentences: it starts with the scope and prerequisite, states the core functionality, and ends with differentiation from alternatives. Every sentence adds value without redundancy, making it efficient and well-structured.

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?

Given the tool's moderate complexity (2 parameters, no output schema) and rich annotations (covering safety and idempotency), the description is largely complete. It explains the tool's purpose, usage context, and behavioral aspects like what is monitored. However, it could briefly mention the tool's stateful nature (starting/stopping monitoring) to enhance completeness, though annotations hint at this with idempotentHint.

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 the schema fully documents both parameters (action with enum values, appIdentifier with default behavior). The description does not add any parameter-specific information beyond what the schema provides, such as explaining the implications of 'start' vs. 'stop' or details about appIdentifier usage. This meets the baseline for high schema coverage.

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?

The description clearly states the tool's purpose with specific verbs ('Monitor', 'Captures') and resources ('Tauri IPC calls between frontend and Rust backend', 'invoke() calls and responses'). It explicitly distinguishes this tool from sibling alternatives by stating 'This is Tauri-specific; for browser network monitoring, use Chrome DevTools MCP,' which differentiates it from webview-related siblings.

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

Usage Guidelines5/5

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

The description provides explicit guidance on when to use this tool vs. alternatives: it specifies the required context ('Requires active tauri_driver_session'), the target scenario ('Tauri Apps Only'), and names an alternative ('for browser network monitoring, use Chrome DevTools MCP'). This covers both prerequisites and exclusions clearly.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/hypothesi/mcp-server-tauri'

If you have feedback or need assistance with the MCP directory API, please join our Discord server