Write/create file
AI agents use write_file to create or update resources in VS Code + GPT Bridge — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your VS Code + GPT Bridge environment.
This tool creates or modifies files on the user's local filesystem. While reversible (files can be edited or deleted later), it poses high severity risk because an AI agent could write malicious code, overwrite critical configuration files, corrupt project files, or write credentials/secrets to disk.
From the tool's definition Tool name is 'write_file' with description 'Write/create file'. The server description confirms it 'Supports file operations (read, write, edit, delete)' on 'local file systems'.
Attacks that exploit this kind of access
Write/create file. It is categorised as a Write tool in the VS Code + GPT Bridge MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the VS Code + GPT Bridge MCP server in PolicyLayer and add a rule for write_file: 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 VS Code + GPT Bridge. Nothing to install.
write_file 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 write_file 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 write_file. 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.
write_file is provided by the VS Code + GPT Bridge MCP server (ndyadav8797-art/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →