Replaces specific lines in existing files with exact content validation. WHEN TO USE: Modifications ≤10 lines where you have exact original text, or inserts of any size. USE create_file_code instead for: new files, large modifications (>10 lines, hard to match exact content), or when original tex...
AI agents use replace_lines_code to create or update resources in Vscode — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Vscode environment.
This tool creates or modifies data reversibly by replacing file contents. While it modifies files, the changes are reversible (can be undone/re-edited), distinguishing it from Destructive. It does not delete or permanently destroy data.
From the tool's definition Tool description states it 'Replaces specific lines in existing files' and 'Modifications', explicitly modifying file content. Parameters include 'originalCode' for exact matching and line number replacement, indicating reversible edits to existing files.
Documented attack patterns abuse exactly the kind of access replace_lines_code gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Vscode, and nothing reaches the server without passing your rules. This is the rule we recommend for replace_lines_code:
{
"version": "1",
"default": "deny",
"tools": {
"replace_lines_code": {
"limits": [
{
"counter": "replace_lines_code_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}replace_lines_code stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Replaces specific lines in existing files with exact content validation. WHEN TO USE: Modifications ≤10 lines where you have exact original text, or inserts of any size. USE create_file_code instead for: new files, large modifications (>10 lines, hard to match exact content), or when original text is uncertain. CRITICAL: originalCode parameter must match current file content exactly or tool fails. If tool fails: run read_file_code on target lines to get current content, then retry. Parameters use 1-based line numbers. Always verify line numbers with read_file_code if unsure. It is categorised as a Write tool in the Vscode MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Vscode MCP server in PolicyLayer and add a rule for replace_lines_code: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Vscode. Nothing to install.
replace_lines_code is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the replace_lines_code rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for replace_lines_code. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
replace_lines_code is provided by the Vscode MCP server (juehang/vscode-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Vscode, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
12 Vscode tools catalogued and risk-classified — across an index of 43,000+ MCP servers.