Skip to main content
Glama

get_screenshot

Capture browser window screenshots during Selenix automation testing. Returns base64-encoded JPEG images for debugging and documentation purposes.

Instructions

Capture a screenshot of the active browser window in Selenix playback. Returns a base64-encoded JPEG image.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • Handler logic that processes the 'get_screenshot' tool result by formatting it as an image content object for MCP.
    if (name === 'get_screenshot' && result.screenshot) {
      const screenshotStr = result.screenshot as string
      const base64Data = screenshotStr.replace(
        /^data:image\/\w+;base64,/,
        ''
      )
      return {
        content: [
          {
            type: 'image' as const,
            data: base64Data,
            mimeType: 'image/jpeg',
          },
          {
            type: 'text' as const,
            text: `Screenshot of: ${result.title || 'unknown'} (${result.url || 'unknown'})`,
          },
        ],
      }
    }
  • Definition and schema for the 'get_screenshot' tool.
    {
      name: 'get_screenshot',
      description:
        'Capture a screenshot of the active browser window in Selenix playback. Returns a base64-encoded JPEG image.',
      inputSchema: {
        type: 'object' as const,
        properties: {},
      },
    },
  • The BridgeClient class acts as the transport layer, calling the Selenix backend API via HTTP. The tool handler uses this to fetch the actual screenshot data.
    export class BridgeClient {
      async call(endpoint: string, body: Record<string, unknown> = {}): Promise<unknown> {
        // Re-read config on every call so we pick up new tokens after Selenix restarts
        const config = readConfig()
    
        return new Promise((resolve, reject) => {
          const data = JSON.stringify(body)
          const req = http.request(
            {
              hostname: '127.0.0.1',
              port: config.port,
              path: `/api/${endpoint}`,
              method: 'POST',
              headers: {
                'Content-Type': 'application/json',
                Authorization: `Bearer ${config.token}`,
                'Content-Length': Buffer.byteLength(data),
              },
              timeout: 180000, // 3 minutes for long-running operations like run_test
            },
            (res) => {
              let responseData = ''
              res.on('data', (chunk: string) => (responseData += chunk))
              res.on('end', () => {
                try {
                  resolve(JSON.parse(responseData))
                } catch {
                  resolve({ raw: responseData })
                }
              })
            }
          )
          req.on('error', (err) =>
            reject(
              new Error(
                `Cannot connect to Selenix bridge at 127.0.0.1:${config.port}. ` +
                  `Is Selenix running with MCP Server enabled? (${err.message})`
              )
            )
          )
          req.on('timeout', () => {
            req.destroy()
            reject(new Error('Request timed out after 180 seconds'))
          })
          req.write(data)
          req.end()
        })
      }
    }

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/markmircea/Selenix-MCP-Server'

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