create_instruction

THE RISK

Medium Risk

Why create_instruction needs a policy

This tool creates or modifies configuration files in the VS Code environment by writing a new .instructions.md file. This is reversible (the file can be deleted or edited), so it falls under Write rather than Destructive.

From the tool's definition Tool creates a new VS Code .instructions.md file with specified description and content. The verb 'Create' combined with writing a file with user-provided content indicates data creation.

Documented attack patterns abuse exactly the kind of access create_instruction gives an agent:

POLICY

How to control create_instruction

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 create_instruction:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "create_instruction": {
      "limits": [
        {
          "counter": "create_instruction_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

create_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.

Create a free account and register Mode Manager MCP — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Mode Manager MCP tools

Destructive delete_instruction Delete a VS Code .instructions.md file from the prompts directory. Write configure_memory_optimization Configure memory optimization settings for auto-optimization behavior. Write optimize_memory Manually optimize a memory file using AI to reorganize and consolidate entries while prese Write remember remember Write update_instruction Update an existing VS Code .instructions.md file with new description or content. Read get_instruction Get the raw content of a VS Code .instructions.md file. Read list_instructions List all VS Code .instructions.md files in the prompts directory. Read memory_stats Get detailed statistics and optimization status for a memory file.

All 9 Mode Manager MCP tools →

Write tools on other servers

M-Team MCP Server download_torrent YouTube MCP Server generate_video_title Android Forensics ADB MCP Server combine_reports 0xarchive web3_signup

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Argument validation → Checking tool call arguments against schema and policy before they run.
Scoped token → Per-person credentials that grant a defined subset of servers and tools.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about create_instruction

What does the create_instruction tool do? +

Create a new VS Code .instructions.md file with the specified description and 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.

How do I enforce a policy on create_instruction? +

Register the Mode Manager MCP server in PolicyLayer and add a rule for create_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.

What risk level is create_instruction? +

create_instruction is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit create_instruction? +

Yes. Add a rate_limit block to the create_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.

How do I block create_instruction completely? +

Set action: deny in the PolicyLayer policy for create_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.

What MCP server provides create_instruction? +

create_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.

Enforce policy on every Mode Manager MCP tool call.

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.

CHECK YOUR STACK →