Skip to main content
Glama
simon-ami

Windows CLI MCP Server

by simon-ami

execute_command

Execute commands in Windows shells (PowerShell, CMD, or Git Bash) with specified working directories for system management and automation tasks.

Instructions

Execute a command in the specified shell (powershell, cmd, or gitbash)

Example usage (PowerShell):

{
  "shell": "powershell",
  "command": "Get-Process | Select-Object -First 5",
  "workingDir": "C:\Users\username"
}

Example usage (CMD):

{
  "shell": "cmd",
  "command": "dir /b",
  "workingDir": "C:\Projects"
}

Example usage (Git Bash):

{
  "shell": "gitbash",
  "command": "ls -la",
  "workingDir": "/c/Users/username"
}

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
shellYesShell to use for command execution
commandYesCommand to execute
workingDirNoWorking directory for command execution (optional)

Implementation Reference

  • src/index.ts:272-323 (registration)
    Registration of the 'execute_command' tool in the ListTools response, including name, detailed description with examples, and input schema definition.
            {
              name: "execute_command",
              description: `Execute a command in the specified shell (powershell, cmd, or gitbash)
    
    Example usage (PowerShell):
    \`\`\`json
    {
      "shell": "powershell",
      "command": "Get-Process | Select-Object -First 5",
      "workingDir": "C:\\Users\\username"
    }
    \`\`\`
    
    Example usage (CMD):
    \`\`\`json
    {
      "shell": "cmd",
      "command": "dir /b",
      "workingDir": "C:\\Projects"
    }
    \`\`\`
    
    Example usage (Git Bash):
    \`\`\`json
    {
      "shell": "gitbash",
      "command": "ls -la",
      "workingDir": "/c/Users/username"
    }
    \`\`\``,
              inputSchema: {
                type: "object",
                properties: {
                  shell: {
                    type: "string",
                    enum: Object.keys(this.config.shells).filter(shell => 
                      this.config.shells[shell as keyof typeof this.config.shells].enabled
                    ),
                    description: "Shell to use for command execution"
                  },
                  command: {
                    type: "string",
                    description: "Command to execute"
                  },
                  workingDir: {
                    type: "string",
                    description: "Working directory for command execution (optional)"
                  }
                },
                required: ["shell", "command"]
              }
            },
  • Runtime input validation schema using Zod that matches the tool's inputSchema.
    const args = z.object({
      shell: z.enum(Object.keys(this.config.shells).filter(shell => 
        this.config.shells[shell as keyof typeof this.config.shells].enabled
      ) as [string, ...string[]]),
      command: z.string(),
      workingDir: z.string().optional()
    }).parse(request.params.arguments);
  • Core handler logic for 'execute_command': validates inputs, spawns the configured shell process, streams and captures stdout/stderr, handles process close/error/timeout, logs to command history if enabled, constructs and returns the tool response with output, error status, and metadata including exit code.
    case "execute_command": {
      const args = z.object({
        shell: z.enum(Object.keys(this.config.shells).filter(shell => 
          this.config.shells[shell as keyof typeof this.config.shells].enabled
        ) as [string, ...string[]]),
        command: z.string(),
        workingDir: z.string().optional()
      }).parse(request.params.arguments);
    
      // Validate command
      this.validateCommand(args.shell as keyof ServerConfig['shells'], args.command);
    
      // Validate working directory if provided
      let workingDir = args.workingDir ? 
        path.resolve(args.workingDir) : 
        process.cwd();
    
      const shellKey = args.shell as keyof typeof this.config.shells;
      const shellConfig = this.config.shells[shellKey];
      
      if (this.config.security.restrictWorkingDirectory) {
        const isAllowedPath = Array.from(this.allowedPaths).some(
          allowedPath => workingDir.startsWith(allowedPath)
        );
    
        if (!isAllowedPath) {
          throw new McpError(
            ErrorCode.InvalidRequest,
            `Working directory (${workingDir}) outside allowed paths. Consult the server admin for configuration changes (config.json - restrictWorkingDirectory, allowedPaths).`
          );
        }
      }
    
      // Execute command
      return new Promise((resolve, reject) => {
        let shellProcess: ReturnType<typeof spawn>;
        
        try {
          shellProcess = spawn(
            shellConfig.command,
            [...shellConfig.args, args.command],
            { cwd: workingDir, stdio: ['pipe', 'pipe', 'pipe'] }
          );
        } catch (err) {
          throw new McpError(
            ErrorCode.InternalError,
            `Failed to start shell process: ${err instanceof Error ? err.message : String(err)}. Consult the server admin for configuration changes (config.json - shells).`
          );
        }
    
        if (!shellProcess.stdout || !shellProcess.stderr) {
          throw new McpError(
            ErrorCode.InternalError,
            'Failed to initialize shell process streams'
          );
        }
    
        let output = '';
        let error = '';
    
        shellProcess.stdout.on('data', (data) => {
          output += data.toString();
        });
    
        shellProcess.stderr.on('data', (data) => {
          error += data.toString();
        });
    
        shellProcess.on('close', (code) => {
          // Prepare detailed result message
          let resultMessage = '';
          
          if (code === 0) {
            resultMessage = output || 'Command completed successfully (no output)';
          } else {
            resultMessage = `Command failed with exit code ${code}\n`;
            if (error) {
              resultMessage += `Error output:\n${error}\n`;
            }
            if (output) {
              resultMessage += `Standard output:\n${output}`;
            }
            if (!error && !output) {
              resultMessage += 'No error message or output was provided';
            }
          }
    
          // Store in history if enabled
          if (this.config.security.logCommands) {
            this.commandHistory.push({
              command: args.command,
              output: resultMessage,
              timestamp: new Date().toISOString(),
              exitCode: code ?? -1
            });
    
            // Trim history if needed
            if (this.commandHistory.length > this.config.security.maxHistorySize) {
              this.commandHistory = this.commandHistory.slice(-this.config.security.maxHistorySize);
            }
          }
    
          resolve({
            content: [{
              type: "text",
              text: resultMessage
            }],
            isError: code !== 0,
            metadata: {
              exitCode: code ?? -1,
              shell: args.shell,
              workingDirectory: workingDir
            }
          });
        });
    
        // Handle process errors (e.g., shell crashes)
        shellProcess.on('error', (err) => {
          const errorMessage = `Shell process error: ${err.message}`;
          if (this.config.security.logCommands) {
            this.commandHistory.push({
              command: args.command,
              output: errorMessage,
              timestamp: new Date().toISOString(),
              exitCode: -1
            });
          }
          reject(new McpError(
            ErrorCode.InternalError,
            errorMessage
          ));
        });
    
        // Set configurable timeout to prevent hanging
        const timeout = setTimeout(() => {
          shellProcess.kill();
          const timeoutMessage = `Command execution timed out after ${this.config.security.commandTimeout} seconds. Consult the server admin for configuration changes (config.json - commandTimeout).`;
          if (this.config.security.logCommands) {
            this.commandHistory.push({
              command: args.command,
              output: timeoutMessage,
              timestamp: new Date().toISOString(),
              exitCode: -1
            });
          }
          reject(new McpError(
            ErrorCode.InternalError,
            timeoutMessage
          ));
        }, this.config.security.commandTimeout * 1000);
    
        shellProcess.on('close', () => clearTimeout(timeout));
      });
    }

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

B3/5.0
Behavior2/5

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

With no annotations provided, the description carries the full burden of disclosing behavior. It gives examples but does not mention return values, exit codes, error handling, side effects, environment specifics, or security implications. For a command execution tool, this is insufficient.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The opening one-sentence description is concise and front-loaded. The three examples are redundant in structure but serve to illustrate cross-shell syntax. Each sentence earns its place, though the examples could be trimmed to one or two without loss.

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?

For a tool that executes arbitrary system commands, there is no mention of output format, timeouts, working directory defaults, or safety considerations. The presence of sibling ssh_execute suggests a need to clarify local vs remote execution, which is absent. The examples help but do not fill all gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already covers 100% of parameters, but the description adds value through concrete examples showing valid shell values, command syntax, and workingDir formatting (e.g., Windows paths vs Git Bash paths). This enhances understanding beyond the schema's terse descriptions.

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 executes a command in a specified shell (powershell, cmd, or gitbash), which is a specific verb+resource. It is distinguishable from siblings like get_command_history and ssh_execute, though it does not explicitly call out these differences. The mention of the shell options adds specificity.

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?

No guidance is given on when to use this tool versus alternatives such as ssh_execute (remote execution) or get_command_history. The examples imply usage but do not provide context, prerequisites, or exclusions. This is a clear gap.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.