AI agents use edit_block to create or update resources in Code — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Code environment.
The tool performs reversible data modification (editing code blocks/files) without permanent deletion or code execution. This is Write category rather than Execute because editing static content differs from running commands. While high severity due to potential code tampering in a project directory, it remains Write rather than Destructive since edits can be reverted via git or manual undo.
From the tool's definition Tool name 'edit_block' is listed among siblings that include 'edit_file', 'delete_path', and 'run_command'. The server description states it 'Enables Claude AI to run terminal commands, perform file operations, and manage git'.
Documented attack patterns abuse exactly the kind of access edit_block gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Code, and nothing reaches the server without passing your rules. This is the rule we recommend for edit_block:
{
"version": "1",
"default": "deny",
"tools": {
"edit_block": {
"limits": [
{
"counter": "edit_block_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}edit_block stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
edit_block. It is categorised as a Write tool in the Code MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Code MCP server in PolicyLayer and add a rule for edit_block: 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 Code. Nothing to install.
edit_block 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 edit_block 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 edit_block. 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.
edit_block is provided by the Code MCP server (54yyyu/code-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 9 Code tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
9 Code tools catalogued and risk-classified — across an index of 42,500+ MCP servers.