Skip to main content
Glama
desamtralized

ADB Screenshot MCP Server

adb_screenshot

Capture screenshots from connected Android devices over WiFi using ADB commands. Save screenshots locally for debugging, documentation, or remote monitoring purposes.

Instructions

Take a screenshot of the connected Android device

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
output_pathNoLocal path to save the screenshot (default: screenshot.png)screenshot.png
device_idNoDevice ID/serial (optional, uses first device if not specified)

Implementation Reference

  • Handler function for the 'adb_screenshot' tool. It takes a screenshot using ADB shell screencap on the device (optionally specified by device_id), pulls it to the local output_path (default 'screenshot.png'), cleans up the temp file on device, and returns a success message.
    case "adb_screenshot": {
      const { output_path = "screenshot.png", device_id } = args as {
        output_path?: string;
        device_id?: string;
      };
    
      const deviceArg = device_id ? `-s ${device_id}` : "";
      const tempPath = "/sdcard/screenshot.png";
    
      // Take screenshot on device
      await execAsync(`adb ${deviceArg} shell screencap -p ${tempPath}`);
      
      // Pull screenshot to local machine
      const { stdout, stderr } = await execAsync(`adb ${deviceArg} pull ${tempPath} ${output_path}`);
      
      // Clean up temp file on device
      await execAsync(`adb ${deviceArg} shell rm ${tempPath}`);
    
      if (stderr && stderr.includes("error")) {
        throw new McpError(ErrorCode.InternalError, `Screenshot failed: ${stderr}`);
      }
    
      return {
        content: [
          {
            type: "text",
            text: `Screenshot saved to ${output_path}`,
          },
        ],
      };
    }
  • Input schema definition for the 'adb_screenshot' tool, defining optional parameters output_path and device_id.
    inputSchema: {
      type: "object",
      properties: {
        output_path: {
          type: "string",
          description: "Local path to save the screenshot (default: screenshot.png)",
          default: "screenshot.png",
        },
        device_id: {
          type: "string",
          description: "Device ID/serial (optional, uses first device if not specified)",
        },
      },
      required: [],
    },
  • src/index.ts:51-70 (registration)
    Registration of the 'adb_screenshot' tool in the ListToolsRequestSchema handler, including name, description, and input schema.
    {
      name: "adb_screenshot",
      description: "Take a screenshot of the connected Android device",
      inputSchema: {
        type: "object",
        properties: {
          output_path: {
            type: "string",
            description: "Local path to save the screenshot (default: screenshot.png)",
            default: "screenshot.png",
          },
          device_id: {
            type: "string",
            description: "Device ID/serial (optional, uses first device if not specified)",
          },
        },
        required: [],
      },
    },
    {
Behavior2/5

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

With no annotations provided, the description carries full burden for behavioral disclosure. It states the action but omits critical details: whether this requires specific permissions, if it's read-only or mutative, potential side effects (e.g., device interaction), error conditions, or output format. This leaves significant gaps in understanding the tool's behavior.

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 a single, efficient sentence with zero wasted words. It is front-loaded with the core action and resource, making it immediately understandable without unnecessary elaboration.

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

Completeness2/5

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

Given no annotations and no output schema, the description is incomplete for a tool that interacts with a device. It lacks details on behavioral traits, error handling, output format, and prerequisites, which are essential for safe and effective use. The simplicity of the tool doesn't compensate for these omissions.

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. The description adds no additional parameter semantics beyond what the schema provides, such as format examples or usage context. Baseline 3 is appropriate when the schema handles all parameter documentation.

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 specific action ('Take a screenshot') and target resource ('connected Android device'), distinguishing it from sibling tools like adb_device_info or adb_list_devices which serve different purposes. It uses precise language that leaves no ambiguity about the tool's function.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives, nor does it mention prerequisites like device connectivity. While it implies usage when a screenshot is needed, it lacks explicit context about timing, dependencies, or comparisons with other tools.

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/desamtralized/adb-mcp'

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