AI agents use write_file to create or update resources in Delta-MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Delta-MCP environment.
This tool creates or modifies file content, which is a reversible operation (files can be edited or deleted afterward). It does not irreversibly destroy data, execute arbitrary code, or move money. Severity is medium because while file writes are generally safe, they could be misused to overwrite important configuration files or data if an agent is not carefully constrained in scope.
From the tool's definition Tool description explicitly states 'Write content to a file in workspace' — a write operation that modifies data reversibly.
Attacks that exploit this kind of access
Write content to a file in workspace. It is categorised as a Write tool in the Delta-MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Delta- 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 Delta-MCP. 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 Delta- MCP server (norhther/delta-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 →