Write file to remote workspace. Auto CRLF→LF and BOM cleanup. Supports optimistic concurrency lock (expectedEtag).
AI agents use remote_write to create or update resources in Mcp Remote Agent — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Remote Agent environment.
This tool creates or modifies files on remote Linux servers, which is a reversible write operation. While the action itself is reversible (files can be re-written or restored), the high severity reflects the significant blast radius of an AI agent writing arbitrary files to production Linux systems—potentially overwriting critical configurations, application code, or data.
From the tool's definition Tool name 'remote_write' and description 'Write file to remote workspace' explicitly indicate file modification capability. The mention of 'expectedEtag' for concurrency control confirms write operations.
Attacks that exploit this kind of access
Write file to remote workspace. Auto CRLF→LF and BOM cleanup. Supports optimistic concurrency lock (expectedEtag). It is categorised as a Write tool in the Mcp Remote Agent MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Remote Agent MCP server in PolicyLayer and add a rule for remote_write: 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 Mcp Remote Agent. Nothing to install.
remote_write 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 remote_write 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 remote_write. 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.
remote_write is provided by the Mcp Remote Agent MCP server (knownothing20/agentport). 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 →