AI agents use write-file to create or update resources in Ssh — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ssh environment.
This tool creates or modifies files on remote servers, which is a reversible write operation. Severity is high because unauthorized file writes on remote systems could modify critical application configuration, inject malicious code into source files, or corrupt data, though the operation is technically reversible (files can be deleted or overwritten).
From the tool's definition Tool name is 'write-file' and description states 'Write content to a file on the remote server' - explicitly creates or modifies data on a remote system.
Attacks that exploit this kind of access
Write content to a file on the remote server. It is categorised as a Write tool in the Ssh MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ssh 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 Ssh. 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 Ssh MCP server (zachflint/ssh-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 →