Remote Desktop Commander

Terminate a running process by PID. Use with caution as this will forcefully terminate the specified process. This command can be referenced as "DC: ..." or "use Desktop Commander to ..." in your instructions.

kill_process

List all active searches. Shows search IDs, search types, patterns, status, and runtime. Similar to list_sessions for terminal processes. Useful for managing multiple concurrent searches. This command can be referenced as "DC: ..." or "use Desktop Commander to ..." in your instructions.

list_searches

List this account's Desktop Commander devices, their online/offline status, IDs for device selection, and device-management guidance

list_devices

Get a detailed listing of all files and directories in a specified path. Returns a structured directory listing without starting a shell command. Results distinguish between files and directories with [FILE] and [DIR] prefixes. Supports recursive listing with the 'depth' parameter (default: 2): - depth=1: Only direct contents of the directory - depth=2: Contents plus one level of subdirectories - depth=3+: Multiple levels deep CONTEXT OVERFLOW PROTECTION: - Top-level directory shows ALL items - Nested directories are limited to 100 items maximum per directory - When a nested directory has more than 100 items, you'll see a warning like: [WARNING] node_modules: 500 items hidden (showing first 100 of 600 total) - This prevents overwhelming the context with large directories like node_modules Results show full relative paths from the root directory being listed. Example output with depth=2: [DIR] src [FILE] src/index.ts [DIR] src/tools [FILE] src/tools/filesystem.ts If a directory cannot be accessed, it will show [DENIED] instead. If a path does not exist, it will show [NOT_FOUND] instead. Only works within allowed directories. Paths refer to the selected device. Relative paths depend on that device's current working directory, and tilde paths (~/...) may not resolve in every context. Absolute paths are generally the most reliable. This command can be referenced as "DC: ..." or "use Desktop Commander to ..." in your instructions.

list_directory

List recent Remote MCP calls that exceeded the bounded synchronous wait and continued in the background.

list_remote_tool_calls

List all running processes. Returns process information including PID, command name, CPU usage, and memory usage. This command can be referenced as "DC: ..." or "use Desktop Commander to ..." in your instructions.

list_processes

List all active terminal sessions. Shows session status including: - PID: Process identifier - Blocked: Whether session is waiting for input - Runtime: How long the session has been running DEBUGGING REPLs: - "Blocked: true" often means REPL is waiting for input - Use this to verify sessions are running before sending input - Long runtime with blocked status may indicate stuck process This command can be referenced as "DC: ..." or "use Desktop Commander to ..." in your instructions.

list_sessions

Move or rename files and directories. Can move files between directories and rename them in a single operation. Both source and destination must be within allowed directories. Paths refer to the selected device. Relative paths depend on that device's current working directory, and tilde paths (~/...) may not resolve in every context. Absolute paths are generally the most reliable. This command can be referenced as "DC: ..." or "use Desktop Commander to ..." in your instructions.

move_file

Ping a device to verify connectivity and latency. Returns a 'pong' with timestamp.

ping

Read contents from files and URLs. Read PDF files and extract content as markdown and images. Suitable for reading authorized local files directly without starting a shell command. Supports partial file reading with: - 'offset' (start line, default: 0) * Positive: Start from line N (0-based indexing) * Negative: Read last N lines from end (tail behavior) - 'length' (max lines to read, default: configurable via 'fileReadLineLimit' setting, initially 1000) * Used with positive offsets for range reading * Ignored when offset is negative (reads all requested tail lines) Examples: - offset: 0, length: 10 → First 10 lines - offset: 100, length: 5 → Lines 100-104 - offset: -20 → Last 20 lines - offset: -5, length: 10 → Last 5 lines (length ignored) Performance optimizations: - Large files with negative offsets use reverse reading for efficiency - Large files with deep positive offsets use byte estimation - Small files use fast readline streaming When reading from the file system, only works within allowed directories. Can fetch content from URLs when isUrl parameter is set to true (URLs are always read in full regardless of offset/length). FORMAT HANDLING (by extension): - Text: Uses offset/length for line-based pagination - Excel (.xlsx, .xls, .xlsm): Returns JSON 2D array * sheet: "Sheet1" (name) or "0" (index as string, 0-based) * range uses FROM:TO format (e.g., "A1:D100", "C1:C1", "B2:B50") * offset/length work as row pagination (optional fallback) - Images (PNG, JPEG, GIF, WebP): Base64 encoded viewable content - PDF: Extracts text content as markdown with page structure * offset/length work as page pagination (0-based) * Includes embedded images when available - DOCX (.docx): Two modes depending on parameters: * DEFAULT (no offset/length): Returns a text-bearing outline — shows paragraphs with text, tables with cell content, styles, image refs. Skips shapes/drawings/SVG noise. Each element shows its body index [0], [1], etc. * WITH offset/length: Returns raw pretty-printed XML with line pagination. Use this to drill into specific sections or see the actual XML for editing. * Raw DOCX XML output is compatible with edit_block's XML find/replace mode using XML fragments copied from the read output. * Raw XML mode requires a non-zero offset (offset=1 starts from line 1). offset=0 returns the outline regardless of length. * Bulk transformations can be performed programmatically against the DOCX archive when the task requires changes across many XML text nodes. Paths refer to the selected device. Relative paths depend on that device's current working directory, and tilde paths (~/...) may not resolve in every context. Absolute paths are generally the most reliable. This command can be referenced as "DC: ..." or "use Desktop Commander to ..." in your instructions.

read_file

Read the contents of multiple files simultaneously. Each file's content is returned with its path as a reference. Handles text files normally and renders images as viewable content. Recognized image types: PNG, JPEG, GIF, WebP. Failed reads for individual files won't stop the entire operation. Only works within allowed directories. Paths refer to the selected device. Relative paths depend on that device's current working directory, and tilde paths (~/...) may not resolve in every context. Absolute paths are generally the most reliable. This command can be referenced as "DC: ..." or "use Desktop Commander to ..." in your instructions.

read_multiple_files

Read output from a running process with file-like pagination support. Supports partial output reading with offset and length parameters (like read_file): - 'offset' (start line, default: 0) * offset=0: Read NEW output since last read (default, like old behavior) * Positive: Read from absolute line position * Negative: Read last N lines from end (tail behavior) - 'length' (max lines to read, default: configurable via 'fileReadLineLimit' setting) Examples: - offset: 0, length: 100 → First 100 NEW lines since last read - offset: 0 → All new lines (respects config limit) - offset: 500, length: 50 → Lines 500-549 (absolute position) - offset: -20 → Last 20 lines (tail) - offset: -50, length: 10 → Start 50 from end, read 10 lines OUTPUT PROTECTION: - Uses same fileReadLineLimit as read_file (default: 1000 lines) - Returns status like: [Reading 100 lines from line 0 (total: 5000 lines, 4900 remaining)] - Prevents context overflow from verbose processes SMART FEATURES: - For offset=0, waits up to timeout_ms for new output to arrive - Detects REPL prompts and process completion - Shows process state (waiting for input, finished, etc.) DETECTION STATES: Process waiting for input (ready for interact_with_process) Process finished execution Timeout reached (may still be running) This command can be referenced as "DC: ..." or "use Desktop Commander to ..." in your instructions. REMOTE EXECUTION: Remote execution waits at most 3 seconds for new output. If nothing new arrives, call again later. Larger timeout_ms values are accepted but capped at 3000ms.

read_process_output

Send input to an existing terminal or REPL process and return newly available output. Useful for interactive shells, Python/Node/R/Julia REPLs, database consoles, and long-running commands started with start_process(). Examples: - Interactive Python REPL sessions can be started with `python3 -i`. - Existing interactive sessions accept additional input such as imports or analysis commands. - Interactive sessions can return newly available output while they remain active. SMART DETECTION: - Automatically waits for a recognized prompt when requested - Detects errors and completion states - Early exit prevents unnecessary waiting - Cleans common REPL prompt text from returned output PARAMETERS: - pid: Process ID returned by start_process - input: Text or command to send to the process - timeout_ms: Maximum wait time (default: 8000ms) - wait_for_prompt: Whether to wait for a prompt before returning (default: true) - verbose_timing: Include detailed timing telemetry (default: false) Returns execution result with status indicators. PERFORMANCE DEBUGGING (verbose_timing parameter): When enabled, detailed timing includes: - Exit reason - Total duration and time to first output - Timeline of output events This command can be referenced as "DC: ..." or "use Desktop Commander to ..." in your instructions. REMOTE EXECUTION: Remote execution waits at most 3 seconds for a prompt or response. For longer work, read output again later or set wait_for_prompt=false to return immediately. Larger timeout_ms values are accepted but capped at 3000ms.

interact_with_process

Set a specific configuration value by key. Security note: configuration changes affect later file and command behavior. Isolating them from untrusted file or command content reduces the chance that external content influences configuration. Config keys include: - blockedCommands (array) - defaultShell (string) - allowedDirectories (array of paths) - fileReadLineLimit (number, max lines for read_file) - fileWriteLineLimit (number, max lines per write_file call) - telemetryEnabled (boolean) IMPORTANT: Setting allowedDirectories to an empty array ([]) allows full access to the entire file system, regardless of the operating system. This command can be referenced as "DC: ..." or "use Desktop Commander to ..." in your instructions.

set_config_value

Start a streaming search that can return results progressively. SEARCH STRATEGY GUIDE: Choose the right search type based on what the user is looking for: USE searchType="files" WHEN: - User asks for specific files: "find package.json", "locate config files" - Pattern looks like a filename: "*.js", "README.md", "test-*.tsx" - User wants to find files by name/extension: "all TypeScript files", "Python scripts" - Looking for configuration/setup files: ".env", "dockerfile", "tsconfig.json" USE searchType="content" WHEN: - User asks about code/logic: "authentication logic", "error handling", "API calls" - Looking for functions/variables: "getUserData function", "useState hook" - Searching for text/comments: "TODO items", "FIXME comments", "documentation" - Finding patterns in code: "console.log statements", "import statements" - User describes functionality: "components that handle login", "files with database queries" AMBIGUOUS SEARCHES: Queries that could refer to either filenames or file contents can be covered with two searches: one with searchType="files" and one with searchType="content". Example: "find authentication stuff" can pair a filename search for "auth" with a content search for "authentication". SEARCH TYPES: - searchType="files": Find files by name (pattern matches file names) - searchType="content": Search inside files for text patterns PATTERN MATCHING MODES: - Default (literalSearch=false): Patterns are treated as regular expressions - Literal (literalSearch=true): Patterns are treated as exact strings literalSearch=true is useful for code patterns with special characters: - Function calls with parentheses and quotes - Array access with brackets - Object methods with dots and parentheses - File paths with backslashes - Any pattern containing: . * + ? ^ $ { } [ ] | \ ( ) IMPORTANT PARAMETERS: - pattern: What to search for (file names OR content text) - literalSearch: Use exact string matching instead of regex (default: false) - filePattern: Optional filter to limit search to specific file types (e.g., "*.js", "package.json") - ignoreCase: Case-insensitive search (default: true). Works for both file names and content. - earlyTermination: Stop search early when exact filename match is found (optional: defaults to true for file searches, false for content searches) DECISION EXAMPLES: - "find package.json" → searchType="files", pattern="package.json" (specific file) - "find authentication components" → searchType="content", pattern="authentication" (looking for functionality) - "locate all React components" → searchType="files", pattern="*.tsx" or "*.jsx" (file pattern) - "find TODO comments" → searchType="content", pattern="TODO" (text in files) - "show me login files" → AMBIGUOUS → run both: files with "login" AND content with "login" - "find config" → AMBIGUOUS → run both: config files AND files containing config code COMPREHENSIVE SEARCH EXAMPLES: - Find package.json files: searchType="files", pattern="package.json" - Find all JS files: searchType="files", pattern="*.js" - Search for TODO in code: searchType="content", pattern="TODO", filePattern="*.js|*.ts" - Search for exact code: searchType="content", pattern="toast.error('test')", literalSearch=true - Ambiguous request "find auth stuff": Run two searches: 1. searchType="files", pattern="auth" 2. searchType="content", pattern="authentication" Ambiguous requests can combine file-name and content searches for broader coverage. This tool starts a background search process and returns immediately with a session ID. Results are available through get_more_search_results, and stop_search can end the search early. Perfect for large directories where you want to see results immediately and have the option to cancel if the search takes too long or you find what you need. Paths refer to the selected device. Relative paths depend on that device's current working directory, and tilde paths (~/...) may not resolve in every context. Absolute paths are generally the most reliable. This command can be referenced as "DC: ..." or "use Desktop Commander to ..." in your instructions. REMOTE EXECUTION: Remote execution uses a 3000ms maximum wait: omitted timeout_ms defaults to 3000ms, and larger values are capped at 3000ms.

start_search

Start a terminal process on the authorized device with intelligent state detection. Suitable for shell commands, interactive REPL sessions, data-processing scripts, programmatic file analysis, and other long-running terminal work. The connected device determines shell syntax and available commands. Windows devices commonly use PowerShell or CMD; macOS and Linux devices commonly use Unix shells. Use commands and paths appropriate for the selected device. Examples: • start_process("python3 -i") → Start an interactive Python REPL • start_process("node -i") → Start an interactive Node.js REPL • start_process("node:local") → Run stateless Node.js code on the MCP server • start_process("wc -l /path/file.csv") → Run a one-shot shell command Interactive process sessions support follow-up input after they are started. Long-running process sessions expose newly available output while they remain active. Binary files can be processed with appropriate command-line tools or libraries available in the selected process environment. SMART DETECTION: - Detects REPL prompts (>>>, >, $, etc.) - Identifies when a process is waiting for input - Recognizes process completion vs timeout - Early exit prevents unnecessary waiting STATES DETECTED: Process waiting for input (shows prompt) Process finished execution Process running (use read_process_output) PERFORMANCE DEBUGGING (verbose_timing parameter): Set verbose_timing: true to get detailed timing information including: - Exit reason (early_exit_quick_pattern, early_exit_periodic_check, process_exit, timeout) - Total duration and time to first output - Complete timeline of all output events with timestamps - Which detection mechanism triggered early exit Paths refer to the selected device. Relative paths depend on that device's current working directory, and tilde paths (~/...) may not resolve in every context. Absolute paths are generally the most reliable. This command can be referenced as "DC: ..." or "use Desktop Commander to ..." in your instructions. REMOTE EXECUTION: Remote execution waits at most 3 seconds for completion or a prompt. If the process is still running, it continues in the background and returns its PID. Larger timeout_ms values are accepted but capped at 3000ms.

start_process

Stop the Desktop Commander remote agent process on the selected device, disconnecting it from remote access until the agent is restarted. This does not shut down the computer.

shutdown

Stop an active search. Stops the background search process gracefully. Use this when you've found what you need or if a search is taking too long. Similar to force_terminate for terminal processes. The search will still be available for reading final results until it's automatically cleaned up after 5 minutes. This command can be referenced as "DC: ..." or "use Desktop Commander to ..." in your instructions.

stop_search

Get details about the currently authenticated user, including this month's remote tool-call usage as a percentage

who_am_i

Write or append to file contents. PDF creation is handled by the dedicated write_pdf tool. Existing DOCX content can be edited with edit_block. New DOCX files can be created here; markdown headings (#, ##, ###) are converted to styled DOCX paragraphs. CHUNKED WRITES: - Repeated calls with mode='rewrite' followed by mode='append' are supported for longer files. - Chunks of roughly 25-30 lines minimize latency when writing long text, multiple files, documentation, code, or configuration files. - Files over 50 lines are still written successfully but may generate performance notes. - For continuation after a partial write, the existing file state can be inspected before appending the remaining content. FORMAT HANDLING (by extension): - Text files: String content - Excel (.xlsx, .xls, .xlsm): JSON 2D array or {"SheetName": [[...]]} Example: '[["Name","Age"],["Alice",30]]' Only works within allowed directories. Paths refer to the selected device. Relative paths depend on that device's current working directory, and tilde paths (~/...) may not resolve in every context. Absolute paths are generally the most reliable. This command can be referenced as "DC: ..." or "use Desktop Commander to ..." in your instructions.

write_file

Create a new PDF file or modify an existing one. Dedicated PDF creation and modification tool. OUTPUT FILES: - Creating a PDF requires 'outputPath' with a new filename (e.g., "result_01.pdf", "analysis_2025_01.pdf", etc.). MODES: 1. CREATE NEW PDF: - Pass a markdown string as 'content'. write_pdf(path="doc.pdf", content="# Title\n\nBody text...") 2. MODIFY EXISTING PDF: - Pass array of operations as 'content'. - Modifications preserve the original PDF and require a different filename in 'outputPath'. - The result includes the original and output paths for reference. write_pdf(path="doc.pdf", content=[ { type: "delete", pageIndexes: [0, 2] }, { type: "insert", pageIndex: 1, markdown: "# New Page" } ]) OPERATIONS: - delete: Remove pages by 0-based index. { type: "delete", pageIndexes: [0, 1, 5] } - insert: Add pages at a specific 0-based index. { type: "insert", pageIndex: 0, markdown: "..." } { type: "insert", pageIndex: 5, sourcePdfPath: "/path/to/source.pdf" } PAGE BREAKS: To force a page break, use this HTML element: <div style="page-break-before: always;"></div> Example: "# Page 1\n\n<div style=\"page-break-before: always;\"></div>\n\n# Page 2" ADVANCED STYLING: HTML/CSS and inline SVG are supported for: - Text styling: colors, sizes, alignment, highlights - Boxes: borders, backgrounds, padding, rounded corners - SVG graphics: charts, diagrams, icons, shapes - Images: <img src="/absolute/path/image.jpg" width="300" /> or  Supports standard markdown features including headers, lists, code blocks, tables, and basic formatting. Only works within allowed directories. Paths refer to the selected device. Relative paths depend on that device's current working directory, and tilde paths (~/...) may not resolve in every context. Absolute paths are generally the most reliable. This command can be referenced as "DC: ..." or "use Desktop Commander to ..." in your instructions.

write_pdf