Skip to main content
Glama
A-Niranjan

MCP Filesystem Server

by A-Niranjan

bash_execute

Execute Bash commands directly with output capture through the MCP Filesystem Server. Provides flexible command execution with security restrictions and environment variable support.

Instructions

Execute a Bash command directly with output capture. More flexible than execute_command but still with security restrictions. Allows for direct access to Bash functionality.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
commandYesThe bash command to execute
workingDirNoWorking directory for command execution
timeoutNoMaximum execution time in milliseconds (max 60s)
envNoAdditional environment variables for the command

Implementation Reference

  • Core handler function that validates and executes the bash command using child_process.exec, captures stdout/stderr/exitCode, with safety checks and logging.
    export async function bashExecute(
      args: z.infer<typeof BashExecuteArgsSchema>,
      config: Config
    ): Promise<{ stdout: string; stderr: string; exitCode: number }> {
      // Validate the command
      validateCommand(args.command)
    
      // Validate working directory if provided
      // Initialize cwd with the current directory and possibly override it
      const cwd = args.workingDir ? await validatePath(args.workingDir, config) : process.cwd()
    
      // Prepare execution options
      const options = {
        cwd,
        timeout: args.timeout || 30000,
        env: args.env ? { ...process.env, ...args.env } : process.env,
        encoding: 'utf8' as const,
        maxBuffer: 10 * 1024 * 1024, // 10MB buffer for output
      }
    
      try {
        await logger.debug(`Executing bash command: ${args.command}`, {
          workingDir: cwd,
          timeout: options.timeout,
        })
    
        // Execute the command
        const { stdout, stderr } = await execPromise(args.command, options)
    
        await logger.debug(`Command executed successfully: ${args.command}`, {
          exitCode: 0,
          stdoutPreview: stdout.substring(0, 100) + (stdout.length > 100 ? '...' : ''),
        })
    
        return {
          stdout,
          stderr,
          exitCode: 0,
        }
      } catch (error: any) {
        // Handle command execution errors
        const stderr = error.stderr || ''
        const stdout = error.stdout || ''
        const exitCode = error.code || 1
    
        await logger.warn(`Command execution failed: ${args.command}`, {
          exitCode,
          stderr: stderr.substring(0, 100) + (stderr.length > 100 ? '...' : ''),
        })
    
        return {
          stdout,
          stderr,
          exitCode,
        }
      }
    }
  • Zod schema defining the input parameters for the bash_execute tool: command, workingDir, timeout, env.
    // Schema for bash_execute arguments
    export const BashExecuteArgsSchema = z.object({
      command: z.string().describe('The bash command to execute'),
      workingDir: z.string().optional().describe('Working directory for command execution'),
      timeout: z
        .number()
        .int()
        .positive()
        .max(60000)
        .optional()
        .default(30000)
        .describe('Maximum execution time in milliseconds (max 60s)'),
      env: z.record(z.string()).optional().describe('Additional environment variables for the command'),
    })
  • MCP-specific handler wrapper: parses args with schema, calls core bashExecute, formats MCP response with content array.
    export async function handleBashExecute(args: any, config: Config) {
      const endMetric = metrics.startOperation('bash_execute')
    
      try {
        // Validate arguments
        const parsed = BashExecuteArgsSchema.safeParse(args)
        if (!parsed.success) {
          throw new FileSystemError(`Invalid arguments for bash_execute`, 'INVALID_ARGS', undefined, {
            errors: parsed.error.format(),
          })
        }
    
        // Execute the command
        const result = await bashExecute(parsed.data, config)
    
        // Format the response
        const formattedResponse = formatCommandResult(result, parsed.data.command)
    
        await logger.debug(`Bash command executed: ${args.command}`, {
          exitCode: result.exitCode,
        })
    
        endMetric()
        return {
          content: [
            {
              type: 'text',
              text: formattedResponse,
            },
          ],
        }
      } catch (error) {
        metrics.recordError('bash_execute')
    
        if (error instanceof FileSystemError) {
          await logger.error(`Error in bash_execute:`, error.toJSON())
          return {
            content: [{ type: 'text', text: `Error: ${error.message}` }],
            isError: true,
          }
        }
    
        const errorMessage = error instanceof Error ? error.message : String(error)
        await logger.error(`Unexpected error in bash_execute:`, { error })
    
        return {
          content: [{ type: 'text', text: `Error: ${errorMessage}` }],
          isError: true,
        }
      }
  • src/index.ts:356-361 (registration)
    Tool definition and schema registration in the listTools handler response.
    name: 'bash_execute',
    description:
      'Execute a Bash command directly with output capture. ' +
      'More flexible than execute_command but still with security restrictions. ' +
      'Allows for direct access to Bash functionality.',
    inputSchema: zodToJsonSchema(BashExecuteArgsSchema) as ToolInput,
  • src/index.ts:757-758 (registration)
    Dispatch/handling registration in the callToolRequest switch statement.
    case 'bash_execute': {
      return await handleBashExecute(a, config)

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/A-Niranjan/mcp-filesystem'

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