// SCAN REPORT

MCP Server for VS Code

25 tools. 12 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 11 Jun 2026

12 can modify or destroy data

13 read-only

25 tools total

Community server · catalogue entry verified 11/06/2026

How to control MCP Server for VS Code ↓

TOOL MAP

What MCP Server for VS Code exposes to your agents

Read (13) Write / Execute (11) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous MCP Server for VS Code tools

Destructive · Medium debug_clearBreakpoints This tool permanently removes all breakpoints from the workspace in a single operation. Execute · High debug_evaluateExpression This tool allows arbitrary expression evaluation in a running debugger session. Execute · High debug_startSession Starting a debug session is fundamentally an Execute operation because it launches and runs code whose behavior depends on the configuration arguments. Execute · High debug_stepOver This tool executes code as part of debugger control flow.

12 of MCP Server for VS Code's 25 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control MCP Server for VS Code

PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Server for VS Code, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "debug_clearBreakpoints": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "debug_toggleBreakpoint": {
    "limits": [
      {
        "counter": "debug_togglebreakpoint_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "callHierarchy": {
    "limits": [
      {
        "counter": "callhierarchy_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register MCP Server for VS Code — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON MCP SERVER FOR VS CODE →

Free to start. No card required.

FULL CATALOGUE

All 25 MCP Server for VS Code tools

DESTRUCTIVE 1 tools

Destructive debug_clearBreakpoints Remove all breakpoints from the workspace

EXECUTE 8 tools

Execute debug_evaluateExpression Evaluate an expression in the current debug context (REPL/watch functionality). Test hypotheses instantly - ex Execute debug_startSession Start a debug session using a configuration from launch.json. Launch debugging instantly - no need to navigate Execute debug_stepOver Step over the current line of code (execute current line without entering functions) Execute debug_stopSession Stop the current debug session Execute debug_continueExecution Continue execution from the current breakpoint or paused state Execute debug_pauseExecution Pause the running debug session at the current execution point Execute debug_stepInto Step into function calls on the current line Execute debug_stepOut Step out of the current function and return to the caller

WRITE 3 tools

Write debug_toggleBreakpoint Toggle a breakpoint on/off at a symbol or file/line location Write debug_setBreakpoint Set a breakpoint by symbol name or file/line with optional conditions. Debug smarter - set breakpoints instant Write refactor_rename Rename a symbol across all files in the workspace. Refactor safely - automatically updates all references, imp

READ 13 tools

Read callHierarchy Find what calls a function or what a function calls by using the function name. Perfect for understanding code Read debug_getCallStack Get the current call stack/stack trace from the paused debug session. Understand execution flow instantly - se Read debug_getOutput Get debug console output from the active debug session (Note: Only works with Read debug_inspectVariables Inspect variables in the current scope (locals, globals, etc.) during debugging. See all variable values insta Read debug_listBreakpoints List all current breakpoints in the workspace. See all breakpoints at once - perfect for debugging complex flo Read debug_listConfigurations List available debug configurations from launch.json Read debug_status Get current debug session status and configuration information Read definition Find the definition of a symbol by name. More efficient than searching files - instantly jumps to where a func Read diagnostics Get diagnostics (errors, warnings, info) for a file or entire workspace. Instantly see all problems without ru Read hover Get hover information (type info, documentation) for a symbol by name. MUCH FASTER than reading entire files w Read references Find all references to a symbol by name. Superior to grep - finds semantic references including imports, type Read symbolSearch Search for symbols (classes, functions, variables) across the workspace. Instant semantic search - finds exact Read workspaceSymbols Get a complete map of all symbols in the workspace (classes, functions, etc). ESSENTIAL for understanding code

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about MCP Server for VS Code

Can an AI agent delete data through the MCP Server for VS Code MCP server? +

Yes. The MCP Server for VS Code server exposes 1 destructive tools including debug_clearBreakpoints. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through MCP Server for VS Code? +

The MCP Server for VS Code server has 3 write tools including debug_toggleBreakpoint, debug_setBreakpoint, refactor_rename. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach MCP Server for VS Code.

How many tools does the MCP Server for VS Code MCP server expose? +

25 tools across 4 categories: Destructive, Execute, Read, Write. 13 are read-only. 12 can modify, create, or delete data.

How do I enforce a policy on MCP Server for VS Code? +

Register the MCP Server for VS Code MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every MCP Server for VS Code tool call.

Deterministic rules across all 25 MCP Server for VS Code tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MCP SERVER FOR VS CODE →

Free to start. No card required.

25 MCP Server for VS Code tools catalogued and risk-classified — across an index of 43,000+ MCP servers.