Skip to main content
Glama

shell_w

Display currently logged-in users and their active processes to monitor system activity through the Shell-MCP server.

Instructions

Show who is logged on and what they are doing

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
argsNoCommand arguments

Implementation Reference

  • Defines the command configuration, description, allowed arguments, and timeout for the 'shell.w' entry, which corresponds to the 'shell_w' MCP tool. This acts as the input validation schema.
    'shell.w': {
      command: 'w',
      description: 'Show who is logged on and what they are doing',
      allowedArgs: ['-h', '-s', '--no-header', '--help'],
      timeout: 2000
    },
  • src/index.ts:27-43 (registration)
    Registers the 'shell_w' tool (from 'shell.w') by dynamically generating tool list with name 'shell_w', description from config, and standard input schema for args array.
    server.setRequestHandler(ListToolsRequestSchema, async () => {
      const tools = Object.entries(allowedCommands).map(([name, config]) => ({
        name: name.replace('shell.', 'shell_'),  // Replace shell. with shell_
        description: config.description,
        inputSchema: {
          type: "object",
          properties: {
            args: {
              type: "array",
              items: { type: "string" },
              description: "Command arguments"
            }
          }
        }
      }));
      return { tools };
    });
  • Generic MCP tool call handler that processes 'shell_w' tool invocations: converts 'shell_w' to 'shell.w', retrieves config and actual command 'w', validates args, executes via executor, and streams stdout as text content.
    server.setRequestHandler(CallToolRequestSchema, async (request) => {
      try {
        const command = String(request.params?.name || '');
        const fullCommand = `shell.${command.replace('shell_', '')}`;  // Replace shell_ back to shell.
        
        if (!(fullCommand in allowedCommands)) {
          return {
            content: [{ type: "text", text: `Unknown command: ${command}` }],
            isError: true
          };
        }
        
        const actualCommand = allowedCommands[fullCommand].command;
        const args = Array.isArray(request.params?.arguments?.args)
          ? request.params.arguments.args.map(String)
          : [];
      
        validator.validateCommand(actualCommand, args);
        const stream = await executor.execute(actualCommand, args);
      
        return {
          content: [{
            type: "text",
            text: await new Promise((resolve, reject) => {
              const chunks: Buffer[] = [];
              stream.stdout.on('data', (chunk: Buffer) => chunks.push(chunk));
              stream.stdout.on('end', () => resolve(Buffer.concat(chunks).toString()));
              stream.stdout.on('error', reject);
            })
          }]
        };
      } catch (error) {
        return {
          content: [{ 
            type: "text", 
            text: `Command execution failed: ${error instanceof Error ? error.message : String(error)}` 
          }],
          isError: true
        };
      }
    });
  • Executes the underlying shell command ('w' for shell_w) by spawning child_process.spawn('w', args), handling security/cache/timeout, and returning stdout stream.
    async execute(
      command: string,
      args: string[] = [],
      options: ExecuteOptions = {}
    ): Promise<{ stdout: Readable }> {
      const commandKey = `${command} ${args.join(' ')}`;
      
      try {
        // Check security
        await this.securityChecker.validateCommand(command, args, options);
    
        // Check cache
        const cached = this.cache.get(commandKey);
        if (cached) {
          this.logger.debug('Using cached command result', { command, args });
          return this.createStreamFromCache(cached);
        }
    
        // Remove 'shell.' prefix for execution
        const baseCommand = command.replace('shell.', '');
    
        // Execute command
        this.logger.debug('Starting command execution', { command, args, options });
        const childProcess = spawn(baseCommand, args, {
          stdio: ['ignore', 'pipe', 'pipe'],
          timeout: options.timeout,
          cwd: options.cwd,
          env: {
            ...process.env,
            ...options.env
          },
          signal: options.signal
        });
    
        this.currentProcess = childProcess;
    
        // Error handling
        childProcess.on('error', (error: Error) => {
          this.logger.error('Command execution error', {
            command,
            args,
            error: error.message
          });
          throw new ToolError(
            'PROCESS_ERROR',
            'Command execution error',
            { command, args, error: error.message }
          );
        });
    
        // Timeout handling
        if (options.timeout) {
          setTimeout(() => {
            if (childProcess.exitCode === null) {
              this.logger.warn('Command execution timeout', {
                command,
                args,
                timeout: options.timeout
              });
              childProcess.kill();
              throw new ToolError(
                'TIMEOUT',
                'Command execution timeout',
                { command, args, timeout: options.timeout }
              );
            }
          }, options.timeout);
        }
    
        if (!childProcess.stdout) {
          throw new ToolError(
            'STREAM_ERROR',
            'Unable to get command output stream',
            { command, args }
          );
        }
    
        // Monitor process status
        childProcess.on('exit', (code, signal) => {
          this.logger.debug('Command execution completed', {
            command,
            args,
            exitCode: code,
            signal
          });
        });
    
        return {
          stdout: childProcess.stdout
        };
  • Validates command and arguments for shell_w using the 'shell.w' config's allowedArgs, path restrictions, and other security checks.
    validateCommand(
      command: string, 
      args: string[] = [], 
      options: CommandOptions = {}
    ): void {
      console.log('Validating command:', {
        command,
        args,
        baseCommand: command.replace('shell.', ''),
        fullCommand: `shell.${command.replace('shell.', '')}`,
        config: allowedCommands[`shell.${command.replace('shell.', '')}`]
      });
    
      const baseCommand = command.replace('shell.', '');
      
      if (!(`shell.${baseCommand}` in allowedCommands)) {
        throw new Error(`Command not allowed: ${command}`);
      }
      
      const config = allowedCommands[`shell.${baseCommand}`];
      
      const allowedArgs = config.allowedArgs || [];
      
      console.log('Checking args:', {
        allowedArgs,
        hasWildcard: allowedArgs.includes('*')
      });
    
      args.forEach(arg => {
        if (arg.startsWith('-')) {
          if (!allowedArgs.includes(arg)) {
            console.log('Invalid option:', arg);
            throw new Error(`Invalid argument: ${arg}`);
          }
        }
        else if (!allowedArgs.includes('*')) {
          console.log('Path not allowed:', arg);
          throw new Error(`Invalid argument: ${arg}`);
        } else {
          // 檢查路徑參數
          this.validatePath(arg);
        }
      });
      
      // 檢查超時設定
      if (options.timeout && options.timeout > securityConfig.defaultTimeout) {
        throw new Error(`Timeout exceeds maximum allowed value`);
      }
    }
Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool's action but does not describe any behavioral traits such as output format, side effects, error handling, or system impact. For a shell command tool with no annotations, this is a significant gap in transparency.

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, clear sentence that directly states the tool's purpose without any unnecessary words. It is front-loaded and efficiently conveys the essential information, making it highly concise and well-structured.

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 the lack of annotations and output schema, the description is incomplete. It does not explain what the tool returns, how it behaves, or any contextual details needed for effective use. For a shell tool with potential system interactions, more information is required to ensure the agent can use it correctly.

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?

The input schema has 100% description coverage, with the 'args' parameter documented as 'Command arguments.' The description does not add any meaning beyond this, as it mentions no parameters. With high schema coverage, the baseline score of 3 is appropriate, as the schema handles the parameter documentation adequately.

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

Purpose4/5

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

The description clearly states the tool's function: 'Show who is logged on and what they are doing.' It specifies the verb ('show') and resource ('who is logged on'), making the purpose unambiguous. However, it does not explicitly differentiate from sibling tools like 'shell_whois' or 'shell_ps', which might have overlapping or related functionality, preventing a perfect score.

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. It does not mention any context, prerequisites, or exclusions, nor does it refer to sibling tools. This lack of usage instructions leaves the agent without direction on appropriate scenarios for invocation.

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/kevinwatt/shell-mcp'

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