Skip to main content
Glama

adb_logcat

Retrieve Android device system logs to debug applications, monitor device activity, and analyze system events using ADB commands.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
filterNoLogcat filter expression (optional)
deviceNoSpecific device ID (optional)
linesNoNumber of lines to return (default: 50)

Implementation Reference

  • The core handler function for the 'adb_logcat' tool. It processes input arguments for device, filter, and lines; constructs the adb logcat command; executes it using runAdb; limits the output to the specified number of lines; and returns the log content or error.
    async (args: z.infer<typeof AdbLogcatSchema>, _extra: RequestHandlerExtra) => {
      const lines = args.lines || 50;
      const filterExpr = args.filter ? args.filter : "";
      log(LogLevel.INFO, `Reading logcat (${lines} lines, filter: ${filterExpr || 'none'})`);
      
      const deviceArgs = buildDeviceArgs(args.device);
      const filterArgs = filterExpr ? splitCommandArguments(filterExpr) : [];
      const adbArgs = [...deviceArgs, "logcat", "-d", ...filterArgs];
    
      try {
        const { stdout, stderr } = await runAdb(adbArgs);
        if (stderr) {
          log(LogLevel.WARN, `logcat returned stderr: ${stderr}`);
        }
    
        const logLines = stdout.split(/\r?\n/);
        const limitedLines = lines > 0 ? logLines.slice(-lines) : logLines;
        const text = limitedLines.join("\n");
    
        return {
          content: [{ type: "text" as const, text }]
        };
      } catch (error) {
        const errorMsg = error instanceof Error ? error.message : String(error);
        log(LogLevel.ERROR, `Error reading logcat: ${errorMsg}`);
        return {
          content: [{ type: "text" as const, text: `Error reading logcat: ${errorMsg}` }],
          isError: true
        };
      }
    },
  • src/index.ts:533-568 (registration)
    Registers the 'adb_logcat' tool with the MCP server via server.tool(), specifying the tool name, input schema shape, inline handler function, and tool description.
    server.tool(
      "adb_logcat",
      AdbLogcatSchema.shape,
      async (args: z.infer<typeof AdbLogcatSchema>, _extra: RequestHandlerExtra) => {
        const lines = args.lines || 50;
        const filterExpr = args.filter ? args.filter : "";
        log(LogLevel.INFO, `Reading logcat (${lines} lines, filter: ${filterExpr || 'none'})`);
        
        const deviceArgs = buildDeviceArgs(args.device);
        const filterArgs = filterExpr ? splitCommandArguments(filterExpr) : [];
        const adbArgs = [...deviceArgs, "logcat", "-d", ...filterArgs];
    
        try {
          const { stdout, stderr } = await runAdb(adbArgs);
          if (stderr) {
            log(LogLevel.WARN, `logcat returned stderr: ${stderr}`);
          }
    
          const logLines = stdout.split(/\r?\n/);
          const limitedLines = lines > 0 ? logLines.slice(-lines) : logLines;
          const text = limitedLines.join("\n");
    
          return {
            content: [{ type: "text" as const, text }]
          };
        } catch (error) {
          const errorMsg = error instanceof Error ? error.message : String(error);
          log(LogLevel.ERROR, `Error reading logcat: ${errorMsg}`);
          return {
            content: [{ type: "text" as const, text: `Error reading logcat: ${errorMsg}` }],
            isError: true
          };
        }
      },
      { description: ADB_LOGCAT_TOOL_DESCRIPTION }
    );
  • Defines the raw input schema object for adb_logcat parameters using Zod primitives with descriptions and defaults.
    export const adbLogcatInputSchema = {
      filter: z.string().optional().describe("Logcat filter expression (optional)"),
      device: z.string().optional().describe("Specific device ID (optional)"),
      lines: z.number().optional().default(50).describe("Number of lines to return (default: 50)")
    };
  • Creates the full Zod schema for adb_logcat by wrapping the input schema with z.object() for validation.
    export const AdbLogcatSchema = z.object(adbLogcatInputSchema);
  • Tool description string used in registration for the adb_logcat tool, providing usage guidance.
     * Tool description for adb-logcat
     */
    const ADB_LOGCAT_TOOL_DESCRIPTION = 
      "Retrieves Android system and application logs from a connected device. " +
      "Ideal for debugging app behavior, monitoring system events, and identifying errors. " +
      "Supports filtering by log tags or expressions to narrow down relevant information. " +
      "Results can be limited to a specific number of lines, making it useful for both brief checks and detailed analysis. " +
      "Use when troubleshooting crashes, unexpected behavior, or performance issues.";
Behavior1/5

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

Tool has no description.

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

Conciseness1/5

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

Tool has no description.

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

Completeness1/5

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

Tool has no description.

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

Parameters1/5

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

Tool has no description.

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

Purpose1/5

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

Tool has no description.

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

Usage Guidelines1/5

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

Tool has no description.

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/srmorete/adb-mcp'

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