Get the raw content of a VS Code .instructions.md file.
AI agents call get_instruction to retrieve information from Mode Manager MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and reads instruction file content without side effects. It matches the Read category definition: queries data with no side effects (get). The severity is low because reading instruction files poses minimal risk; the data retrieved is typically configuration or documentation text, and there is no capability to execute, modify, or delete content.
From the tool's definition Tool description states 'Get the raw content of a VS Code .instructions.md file' — a pure retrieval operation with no modification, deletion, or execution capability.
Documented attack patterns abuse exactly the kind of access get_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 get_instruction:
{
"version": "1",
"default": "deny",
"tools": {
"get_instruction": {}
}
}get_instruction is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get the raw content of a VS Code .instructions.md file. It is categorised as a Read tool in the Mode Manager MCP MCP Server, which means it retrieves data without modifying state.
Register the Mode Manager MCP server in PolicyLayer and add a rule for get_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.
get_instruction is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_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 get_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.
get_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.