Skip to main content
Glama

dump_image

Capture screenshots from Android devices via ADB and return them as files or base64 data for debugging, testing, or documentation purposes.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
deviceNoSpecific device ID (optional)
asBase64NoReturn image as base64 (default: false)

Implementation Reference

  • The handler function that executes the dump_image tool logic: runs 'adb shell screencap -p /sdcard/screenshot.png', pulls the PNG to a temp file, cleans up remote file, reads it, and returns base64 if requested or success message.
    async (args: z.infer<typeof AdbScreenshotSchema>, _extra: RequestHandlerExtra) => {
      log(LogLevel.INFO, "Taking device screenshot");
      
      const deviceArgs = buildDeviceArgs(args.device);
      const tempFilePath = createTempFilePath("adb-mcp", "screenshot.png");
      const remotePath = "/sdcard/screenshot.png";
      
      try {
        // Take screenshot on the device
        await runAdb([...deviceArgs, "shell", "screencap", "-p", remotePath]);
        
        // Pull the screenshot from the device
        await runAdb([...deviceArgs, "pull", remotePath, tempFilePath]);
        
        // Clean up the remote file
        await runAdb([...deviceArgs, "shell", "rm", remotePath]);
        
        // Read the screenshot file
        const imageData = await readFilePromise(tempFilePath);
        
        // Return as base64 or success message based on asBase64 parameter
        if (args.asBase64) {
          const base64Image = imageData.toString('base64');
          log(LogLevel.INFO, "Screenshot captured and converted to base64 successfully");
          return {
            content: [{ type: "text" as const, text: base64Image }]
          };
        } else {
          log(LogLevel.INFO, "Screenshot captured successfully");
          return {
            content: [{ type: "text" as const, text: "Screenshot captured successfully" }]
          };
        }
      } catch (error) {
        const errorMsg = error instanceof Error ? error.message : String(error);
        log(LogLevel.ERROR, `Error taking screenshot: ${errorMsg}`);
        return {
          content: [{ type: "text" as const, text: `Error taking screenshot: ${errorMsg}` }],
          isError: true
        };
      } finally {
        // Clean up the temporary file
        await cleanupTempFile(tempFilePath);
      }
    },
  • Base input schema object for dump_image tool parameters.
    export const dumpImageInputSchema = {
      device: z.string().optional().describe("Specific device ID (optional)"),
      asBase64: z.boolean().optional().default(false).describe("Return image as base64 (default: false)")
    };
  • Zod schema wrapper used for dump_image tool input validation in registration.
    export const AdbScreenshotSchema = z.object(dumpImageInputSchema);
  • src/index.ts:666-715 (registration)
    MCP server.tool registration for the 'dump_image' tool, specifying name, input schema, handler function, and description.
    server.tool(
      "dump_image",
      AdbScreenshotSchema.shape,
      async (args: z.infer<typeof AdbScreenshotSchema>, _extra: RequestHandlerExtra) => {
        log(LogLevel.INFO, "Taking device screenshot");
        
        const deviceArgs = buildDeviceArgs(args.device);
        const tempFilePath = createTempFilePath("adb-mcp", "screenshot.png");
        const remotePath = "/sdcard/screenshot.png";
        
        try {
          // Take screenshot on the device
          await runAdb([...deviceArgs, "shell", "screencap", "-p", remotePath]);
          
          // Pull the screenshot from the device
          await runAdb([...deviceArgs, "pull", remotePath, tempFilePath]);
          
          // Clean up the remote file
          await runAdb([...deviceArgs, "shell", "rm", remotePath]);
          
          // Read the screenshot file
          const imageData = await readFilePromise(tempFilePath);
          
          // Return as base64 or success message based on asBase64 parameter
          if (args.asBase64) {
            const base64Image = imageData.toString('base64');
            log(LogLevel.INFO, "Screenshot captured and converted to base64 successfully");
            return {
              content: [{ type: "text" as const, text: base64Image }]
            };
          } else {
            log(LogLevel.INFO, "Screenshot captured successfully");
            return {
              content: [{ type: "text" as const, text: "Screenshot captured successfully" }]
            };
          }
        } catch (error) {
          const errorMsg = error instanceof Error ? error.message : String(error);
          log(LogLevel.ERROR, `Error taking screenshot: ${errorMsg}`);
          return {
            content: [{ type: "text" as const, text: `Error taking screenshot: ${errorMsg}` }],
            isError: true
          };
        } finally {
          // Clean up the temporary file
          await cleanupTempFile(tempFilePath);
        }
      },
      { description: ADB_DUMP_IMAGE_TOOL_DESCRIPTION }
    );
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