Apply unified diff or structured edits
AI agents use apply_patch to create or update resources in Coding MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Coding MCP Server environment.
Applying a patch modifies existing files by overwriting portions of their content. This is a Write operation (reversible via git), but the blast radius is high because a misapplied patch can corrupt source files across a project. It does not irreversibly delete data on its own (changes can be reverted via git), so Destructive is not chosen, but it ranks high severity due to potential widespread file modification.
From the tool's definition Apply unified diff or structured edits
Attacks that exploit this kind of access
Apply unified diff or structured edits. It is categorised as a Write tool in the Coding MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Coding MCP Server MCP server in PolicyLayer and add a rule for apply_patch: 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 Coding MCP Server. Nothing to install.
apply_patch 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 apply_patch 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 apply_patch. 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.
apply_patch is provided by the Coding MCP Server MCP server (kieutrongthien/coding-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 →