Write text content to a file on the local machine. Creates parent directories if needed. Overwrites existing files. Use this for creating or replacing any text file (source code, markdown, JSON, config files, etc.) - no shell quoting, no encoding issues, full Unicode support. For appending to a f...
AI agents use write_file to create or update resources in Self-hosted MCP server for Claude — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Self-hosted MCP server for Claude environment.
This tool creates or modifies local files, which is a Write operation. Severity is high because an AI agent could maliciously overwrite critical configuration files, source code, or system files on the user's machine, potentially causing significant operational disruption or enabling further attacks.
From the tool's definition Tool description states it "Write[s] text content to a file on the local machine" and "Overwrites existing files." It creates or modifies files reversibly.
Attacks that exploit this kind of access
Write text content to a file on the local machine. Creates parent directories if needed. Overwrites existing files. Use this for creating or replacing any text file (source code, markdown, JSON, config files, etc.) - no shell quoting, no encoding issues, full Unicode support. For appending to a file, use mode=. It is categorised as a Write tool in the Self-hosted MCP server for Claude MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Self-hosted MCP server for Claude 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 Self-hosted MCP server for Claude. 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 Self-hosted MCP server for Claude MCP server (leszczynskikarol/mcp-server). 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 →