Skip to main content
Glama

write_file

Write or overwrite a file with new content, automatically creating parent directories as needed.

Instructions

Write or overwrite a file with new content. Creates parent directories automatically.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pathYesFile path
contentYesContent to write
workspace_rootNoWorkspace root directory (optional)

Implementation Reference

  • The handler function that executes the write_file tool logic. It resolves the workspace path, creates parent directories, writes the file content, and returns a success message.
    case "write_file": {
      const filePath = resolveWorkspacePath(a.path as string, a.workspace_root as string | undefined);
      await mkdir(dirname(filePath), { recursive: true });
      await writeFile(filePath, a.content as string, "utf-8");
      return { content: [{ type: "text", text: `Written: ${filePath}` }] };
    }
  • The input schema definition for the write_file tool, specifying 'path' (string, required) and 'content' (string, required) properties.
      name: "write_file",
      description: "Write or overwrite a file with new content. Creates parent directories automatically.",
      inputSchema: {
        type: "object",
        properties: {
          path: { type: "string", description: "File path" },
          content: { type: "string", description: "Content to write" },
          workspace_root: { type: "string", description: "Workspace root directory (optional)" },
        },
        required: ["path", "content"],
      },
    },
  • src/index.ts:166-422 (registration)
    The TOOLS array where write_file is registered alongside all other tools. Line 182 is the start of the write_file entry in this array.
    const TOOLS: Tool[] = [
      {
        name: "read_file",
        description: "Read the contents of a file. Optionally specify a line range.",
        inputSchema: {
          type: "object",
          properties: {
            path: { type: "string", description: "File path (absolute or relative to workspace root)" },
            start_line: { type: "number", description: "First line to read (1-indexed, inclusive)" },
            end_line: { type: "number", description: "Last line to read (1-indexed, inclusive)" },
            workspace_root: { type: "string", description: "Workspace root directory (optional)" },
          },
          required: ["path"],
        },
      },
      {
        name: "write_file",
        description: "Write or overwrite a file with new content. Creates parent directories automatically.",
        inputSchema: {
          type: "object",
          properties: {
            path: { type: "string", description: "File path" },
            content: { type: "string", description: "Content to write" },
            workspace_root: { type: "string", description: "Workspace root directory (optional)" },
          },
          required: ["path", "content"],
        },
      },
      {
        name: "edit_file",
        description: "Replace an exact string in a file. The old_string must appear exactly once.",
        inputSchema: {
          type: "object",
          properties: {
            path: { type: "string", description: "File path" },
            old_string: { type: "string", description: "Exact text to find and replace" },
            new_string: { type: "string", description: "Text to replace it with" },
            workspace_root: { type: "string", description: "Workspace root directory (optional)" },
          },
          required: ["path", "old_string", "new_string"],
        },
      },
      {
        name: "list_directory",
        description: "List files and directories at a given path.",
        inputSchema: {
          type: "object",
          properties: {
            path: { type: "string", description: "Directory path" },
            recursive: { type: "boolean", description: "Whether to list recursively (default false)" },
            workspace_root: { type: "string", description: "Workspace root directory (optional)" },
          },
          required: ["path"],
        },
      },
      {
        name: "create_directory",
        description: "Create a directory (and all parent directories).",
        inputSchema: {
          type: "object",
          properties: {
            path: { type: "string", description: "Directory path to create" },
            workspace_root: { type: "string", description: "Workspace root directory (optional)" },
          },
          required: ["path"],
        },
      },
      {
        name: "delete_path",
        description: "Delete a file or directory.",
        inputSchema: {
          type: "object",
          properties: {
            path: { type: "string", description: "File or directory path to delete" },
            recursive: { type: "boolean", description: "Required true to delete non-empty directories" },
            workspace_root: { type: "string", description: "Workspace root directory (optional)" },
          },
          required: ["path"],
        },
      },
      {
        name: "move_path",
        description: "Move or rename a file or directory.",
        inputSchema: {
          type: "object",
          properties: {
            source: { type: "string", description: "Source path" },
            destination: { type: "string", description: "Destination path" },
            workspace_root: { type: "string", description: "Workspace root directory (optional)" },
          },
          required: ["source", "destination"],
        },
      },
      {
        name: "search_files",
        description: "Search for a regex pattern inside files. Returns matching lines with file and line number.",
        inputSchema: {
          type: "object",
          properties: {
            directory: { type: "string", description: "Directory to search in" },
            pattern: { type: "string", description: "Regex pattern to search for" },
            file_glob: { type: "string", description: "Glob to filter files (e.g. '*.ts')" },
            ignore_case: { type: "boolean", description: "Case-insensitive search" },
            max_results: { type: "number", description: "Max results to return (default 100)" },
            workspace_root: { type: "string", description: "Workspace root directory (optional)" },
          },
          required: ["directory", "pattern"],
        },
      },
      {
        name: "find_files",
        description: "Find files by name glob pattern (e.g. '*.ts', 'index.*').",
        inputSchema: {
          type: "object",
          properties: {
            directory: { type: "string", description: "Directory to search in" },
            pattern: { type: "string", description: "Glob pattern for filename (e.g. '*.ts')" },
            max_results: { type: "number", description: "Max results to return (default 200)" },
            workspace_root: { type: "string", description: "Workspace root directory (optional)" },
          },
          required: ["directory", "pattern"],
        },
      },
      {
        name: "run_command",
        description: "Execute a shell command in the given working directory. Returns stdout, stderr, and exit code.",
        inputSchema: {
          type: "object",
          properties: {
            command: { type: "string", description: "Command to run" },
            cwd: { type: "string", description: "Working directory (defaults to workspace root or cwd)" },
            timeout_ms: { type: "number", description: "Timeout in milliseconds (default 30000)" },
          },
          required: ["command"],
        },
      },
      {
        name: "get_workspace_info",
        description: "Get information about the current workspace: root directory, platform, Node version, git status summary.",
        inputSchema: {
          type: "object",
          properties: {
            workspace_root: { type: "string", description: "Workspace root directory (optional)" },
          },
        },
      },
      {
        name: "get_file_info",
        description: "Get metadata about a file or directory (size, modification time, type).",
        inputSchema: {
          type: "object",
          properties: {
            path: { type: "string", description: "File or directory path" },
            workspace_root: { type: "string", description: "Workspace root directory (optional)" },
          },
          required: ["path"],
        },
      },
    
      // ── Cursor bridge tools (require the cursor-mcp-bridge extension running) ──
      {
        name: "cursor_status",
        description: "Check if the Cursor MCP Bridge extension is running and get workspace info.",
        inputSchema: { type: "object", properties: {} },
      },
      {
        name: "cursor_list_commands",
        description: "List Cursor/VS Code commands available in the IDE. Use filter to narrow results.",
        inputSchema: {
          type: "object",
          properties: {
            filter: { type: "string", description: "Optional keyword filter (e.g. 'chat', 'model', 'cursor')" },
          },
        },
      },
      {
        name: "cursor_open_chat",
        description: "Open a new chat, composer, or agent panel in Cursor.",
        inputSchema: {
          type: "object",
          properties: {
            mode: {
              type: "string",
              enum: ["chat", "composer", "agent"],
              description: "Which panel to open (default: chat)",
            },
            message: { type: "string", description: "Optional initial message to send" },
          },
        },
      },
      {
        name: "cursor_send_message",
        description: "Open the Cursor chat and send a message (starts a new conversation).",
        inputSchema: {
          type: "object",
          properties: {
            message: { type: "string", description: "Message to send in the chat" },
          },
          required: ["message"],
        },
      },
      {
        name: "cursor_get_model",
        description: "Get the currently configured AI model in Cursor.",
        inputSchema: { type: "object", properties: {} },
      },
      {
        name: "cursor_set_model",
        description: "Change the active AI model in Cursor (e.g. claude-sonnet-4-5, gpt-4o, gemini-pro).",
        inputSchema: {
          type: "object",
          properties: {
            model: { type: "string", description: "Model identifier to set" },
          },
          required: ["model"],
        },
      },
      {
        name: "cursor_open_model_picker",
        description: "Open the model selector UI in Cursor so the user can pick a model visually.",
        inputSchema: { type: "object", properties: {} },
      },
      {
        name: "cursor_open_file",
        description: "Open a file in the Cursor editor, optionally jumping to a specific line.",
        inputSchema: {
          type: "object",
          properties: {
            path: { type: "string", description: "Absolute file path to open" },
            line: { type: "number", description: "Line number to jump to (1-indexed)" },
          },
          required: ["path"],
        },
      },
      {
        name: "cursor_editor_state",
        description: "Get the current editor state: active file, cursor position, selected text, open editors.",
        inputSchema: { type: "object", properties: {} },
      },
      {
        name: "cursor_diagnostics",
        description: "Get all errors and warnings (diagnostics) from the IDE's language servers.",
        inputSchema: { type: "object", properties: {} },
      },
      {
        name: "cursor_run_command",
        description: "Execute any VS Code / Cursor command by its ID. Use cursor_list_commands to discover IDs.",
        inputSchema: {
          type: "object",
          properties: {
            command: { type: "string", description: "Command ID (e.g. 'workbench.action.reloadWindow')" },
            args: { type: "array", description: "Optional arguments to pass to the command" },
          },
          required: ["command"],
        },
      },
    ];
  • Import of writeFile from fs/promises, which is the actual Node.js filesystem function used by the handler.
    import { readFile, writeFile, mkdir, rm, readdir, stat, rename } from "fs/promises";
Behavior3/5

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

With no annotations, the description must bear the full burden of behavioral disclosure. It mentions that parent directories are created automatically, which is a key side effect. However, it does not disclose other traits such as whether existing content is truncated, permission requirements, or any failure modes (e.g., if file is locked).

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 concise, consisting of two sentences with no redundant words. It is front-loaded with the primary action and immediately follows with a key behavioral detail.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is simple with three parameters and no output schema. The description covers the core action (write/overwrite) and an important side effect (auto-create directories). However, given the presence of siblings like edit_file, a brief usage note would improve completeness.

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?

All three parameters are described in the input schema with 100% coverage, so the baseline is 3. The tool description adds no additional semantic value beyond the schema descriptions, such as the format or constraints on content or path.

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 verb 'Write or overwrite' and the resource 'file', and it adds the detail 'Creates parent directories automatically', which distinguishes it from sibling tools like create_directory that might not handle directory creation automatically.

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 does not provide any guidance on when to use this tool versus alternatives such as edit_file or create_directory. There is no explicit 'when-not' or mention of prerequisites, leaving the agent without contextual decision support.

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/KloutDevs/vscode-mcp'

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