Skip to main content
Glama
simon-ami

Windows CLI MCP Server

ssh_execute

Execute commands on remote hosts via SSH to manage systems, run scripts, or retrieve information from connected devices.

Instructions

Execute a command on a remote host via SSH

Example usage:

{
  "connectionId": "raspberry-pi",
  "command": "uname -a"
}

Configuration required in config.json:

{
  "ssh": {
    "enabled": true,
    "connections": {
      "raspberry-pi": {
        "host": "raspberrypi.local",
        "port": 22,
        "username": "pi",
        "password": "raspberry"
      }
    }
  }
}

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
connectionIdYesID of the SSH connection to use
commandYesCommand to execute

Implementation Reference

  • Main handler for the ssh_execute tool: validates input, retrieves SSH connection from pool, executes command, handles response and logging.
    case "ssh_execute": {
      if (!this.config.ssh.enabled) {
        throw new McpError(
          ErrorCode.InvalidRequest,
          "SSH support is disabled in configuration"
        );
      }
    
      const args = z.object({
        connectionId: z.string(),
        command: z.string()
      }).parse(request.params.arguments);
    
      const connectionConfig = this.config.ssh.connections[args.connectionId];
      if (!connectionConfig) {
        throw new McpError(
          ErrorCode.InvalidRequest,
          `Unknown SSH connection ID: ${args.connectionId}`
        );
      }
    
      try {
        // Validate command
        this.validateCommand('cmd', args.command);
    
        const connection = await this.sshPool.getConnection(args.connectionId, connectionConfig);
        const { output, exitCode } = await connection.executeCommand(args.command);
    
        // Store in history if enabled
        if (this.config.security.logCommands) {
          this.commandHistory.push({
            command: args.command,
            output,
            timestamp: new Date().toISOString(),
            exitCode,
            connectionId: args.connectionId
          });
    
          if (this.commandHistory.length > this.config.security.maxHistorySize) {
            this.commandHistory = this.commandHistory.slice(-this.config.security.maxHistorySize);
          }
        }
    
        return {
          content: [{
            type: "text",
            text: output || 'Command completed successfully (no output)'
          }],
          isError: exitCode !== 0,
          metadata: {
            exitCode,
            connectionId: args.connectionId
          }
        };
      } catch (error) {
        const errorMessage = error instanceof Error ? error.message : String(error);
        if (this.config.security.logCommands) {
          this.commandHistory.push({
            command: args.command,
            output: `SSH error: ${errorMessage}`,
            timestamp: new Date().toISOString(),
            exitCode: -1,
            connectionId: args.connectionId
          });
        }
        throw new McpError(
          ErrorCode.InternalError,
          `SSH error: ${errorMessage}`
        );
      }
    }
  • Input schema definition for ssh_execute tool specifying connectionId and command parameters.
    inputSchema: {
      type: "object",
      properties: {
        connectionId: {
          type: "string",
          description: "ID of the SSH connection to use",
          enum: Object.keys(this.config.ssh.connections)
        },
        command: {
          type: "string",
          description: "Command to execute"
        }
      },
      required: ["connectionId", "command"]
    }
  • src/index.ts:356-399 (registration)
    Registration of ssh_execute tool in the list of available tools, including name, description, and schema.
            {
              name: "ssh_execute",
              description: `Execute a command on a remote host via SSH
    
    Example usage:
    \`\`\`json
    {
      "connectionId": "raspberry-pi",
      "command": "uname -a"
    }
    \`\`\`
    
    Configuration required in config.json:
    \`\`\`json
    {
      "ssh": {
        "enabled": true,
        "connections": {
          "raspberry-pi": {
            "host": "raspberrypi.local",
            "port": 22,
            "username": "pi",
            "password": "raspberry"
          }
        }
      }
    }
    \`\`\``,
              inputSchema: {
                type: "object",
                properties: {
                  connectionId: {
                    type: "string",
                    description: "ID of the SSH connection to use",
                    enum: Object.keys(this.config.ssh.connections)
                  },
                  command: {
                    type: "string",
                    description: "Command to execute"
                  }
                },
                required: ["connectionId", "command"]
              }
            },
  • Core SSH command execution logic using ssh2 Client.exec, capturing stdout/stderr and exit code.
    async executeCommand(command: string): Promise<{ output: string; exitCode: number }> {
      this.lastActivity = Date.now();
    
      // Check connection and attempt reconnect if needed
      if (!this.isConnected) {
        await this.connect();
      }
    
      return new Promise((resolve, reject) => {
        this.client.exec(command, (err, stream) => {
          if (err) {
            reject(err);
            return;
          }
    
          let output = '';
          let errorOutput = '';
    
          stream
            .on('data', (data: Buffer) => {
              output += data.toString();
            })
            .stderr.on('data', (data: Buffer) => {
              errorOutput += data.toString();
            });
    
          stream.on('close', (code: number) => {
            this.lastActivity = Date.now();
            resolve({
              output: output || errorOutput,
              exitCode: code || 0
            });
          });
        });
      });
    }
  • SSHConnectionPool method to acquire or create and connect an SSHConnection instance.
    async getConnection(connectionId: string, config: SSHConnectionConfig): Promise<SSHConnection> {
      let connection = this.connections.get(connectionId);
      
      if (!connection) {
        connection = new SSHConnection(config);
        this.connections.set(connectionId, connection);
        await connection.connect();
      } else if (!connection.isActive()) {
        await connection.connect();
      }
    
      return connection;
    }
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. It discloses that SSH configuration is required and shows an example, but does not mention critical behavioral traits such as authentication needs (e.g., password/key-based), potential security risks, execution timeouts, error handling, or output format. For a tool that executes commands remotely, 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.

Conciseness4/5

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

The description is appropriately sized and front-loaded with the core purpose in the first sentence. The example and configuration details are relevant but could be more concise; however, they earn their place by clarifying usage and prerequisites without unnecessary verbosity.

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 complexity of SSH command execution, no annotations, and no output schema, the description is incomplete. It lacks information on return values (e.g., stdout, stderr, exit codes), error conditions, security implications, and behavioral details like interactive vs. non-interactive execution. The example helps but does not compensate for these gaps.

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 already documents both parameters ('connectionId' and 'command') with descriptions. The description adds minimal value beyond the schema by showing an example usage that illustrates parameter values, but does not provide additional semantic context like command syntax constraints or connectionId enumeration details.

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 ('Execute a command') and resource ('on a remote host via SSH'), distinguishing it from siblings like 'create_ssh_connection' (setup) or 'get_command_history' (retrieval). The example usage reinforces this purpose with concrete parameters.

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

Usage Guidelines3/5

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

The description implies usage by showing an example with 'connectionId' and 'command', and mentions configuration prerequisites, but does not explicitly state when to use this tool versus alternatives like 'execute_command' (which might be a sibling with unclear differentiation) or provide exclusions. The context is clear but lacks explicit guidance on tool selection.

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/simon-ami/win-cli-mcp-server'

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