Update an existing VS Code .instructions.md file with new description or content.
AI agents use update_instruction to create or update resources in Mode Manager MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mode Manager MCP environment.
The tool creates or modifies data (VS Code instruction files) in a reversible manner. It does not delete or irreversibly destroy data (which would be Destructive), nor does it execute arbitrary code or external operations (which would be Execute). The modification is scoped to configuration/instruction files rather than critical system data, placing severity at medium rather than high.
From the tool's definition Tool description states 'Update an existing VS Code .instructions.md file with new description or content' — this modifies file content reversibly.
Documented attack patterns abuse exactly the kind of access update_instruction gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mode Manager MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for update_instruction:
{
"version": "1",
"default": "deny",
"tools": {
"update_instruction": {
"limits": [
{
"counter": "update_instruction_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update_instruction 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.
Update an existing VS Code .instructions.md file with new description or content. It is categorised as a Write tool in the Mode Manager MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mode Manager MCP server in PolicyLayer and add a rule for update_instruction: 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 Mode Manager MCP. Nothing to install.
update_instruction 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 update_instruction 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 update_instruction. 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.
update_instruction is provided by the Mode Manager MCP server (niclasolofsson/mode-manager-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mode Manager MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
9 Mode Manager MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.