vs-code-mcp-server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
| prompts | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_files_codeA | List files and directories in a specified path with optional recursive listing |
| read_file_codeA | Read the contents of a file with optional encoding and line range |
| create_file_codeC | Create a new file or overwrite an existing file with content |
| delete_file_codeB | Delete a file or directory |
| copy_file_codeB | Copy a file or directory to another location |
| move_file_codeB | Move or rename a file or directory |
| create_directory_codeC | Create a new directory |
| search_files_codeC | Search for text patterns in files within a directory |
| replace_lines_codeB | Replace specific lines in existing files with exact content validation |
| insert_lines_codeB | Insert new lines at a specific position in a file |
| delete_lines_codeB | Delete specific lines from a file |
| append_to_file_codeB | Append content to the end of a file |
| prepend_to_file_codeA | Prepend content to the beginning of a file |
| find_and_replace_codeA | Find and replace text patterns in a file with regex support |
| execute_shell_command_codeC | Execute shell commands in VS Code integrated terminal |
| execute_streaming_command_codeC | Execute shell commands with streaming output |
| kill_process_codeA | Kill a process by PID or name |
| list_processes_codeB | List running processes with filtering options |
| kill_all_processes_codeB | Kill all processes matching a pattern (use with caution) |
| check_command_codeA | Check if a command is available on the system |
| get_system_info_codeA | Get system information including OS, CPU, memory, and disk usage |
| run_script_codeC | Run a script file with the appropriate interpreter |
| analyze_projectC | Analyze project structure and provide insights about the codebase |
| get_project_statsC | Get detailed statistics about the project codebase |
| find_dependenciesC | Find and analyze project dependencies |
| search_symbols_codeA | Search for symbols (functions, classes, variables) across workspace using fuzzy matching |
| get_symbol_definition_codeB | Gets definition information for a symbol using hover data (type, docs, source) |
| get_document_symbols_codeA | Gets complete symbol outline for a file showing hierarchical structure and line numbers |
| get_diagnostics_codeC | Analyzes code for warnings and errors using integrated linters |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 29 tools
Most tools have clearly distinct purposes, such as file operations versus process management. However, execute_shell_command_code and execute_streaming_command_code are similar, and several file editing tools (replace_lines, insert_lines, find_and_replace) could be confused despite their specific descriptions.
The majority of tools follow a verb_noun_code pattern (e.g., list_files_code, read_file_code). However, a few tools omit the '_code' suffix (analyze_project, get_project_stats, find_dependencies), creating inconsistency in the naming convention.
With 29 tools, the server pushes beyond the typical upper bound for a well-scoped toolset. The breadth of file, code analysis, and system operations justifies a large surface, but the count feels excessive and could overwhelm agents.
The toolset provides comprehensive coverage for file operations (create, read, update, delete, search) and code analysis (symbols, diagnostics, project insights). Minor gaps exist, such as no direct tool to inspect file metadata or manage editor tabs, but these are not critical for the domain.