elevate_foundation · Decision OS MCP: Risk & Policy

WHAT IT DOES

What elevate_foundation does on Decision OS MCP

AI agents use elevate_foundation to create or update resources in Decision OS MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Decision OS MCP environment.

WHY IT NEEDS A POLICY

Why elevate_foundation needs a policy

This tool copies/promotes a project-specific foundation entry to a global scope location (~/.decision-os). It creates a new global record (write operation) but does not delete the original, making it reversible in principle. Misuse could pollute the global knowledge base with incorrect or premature learnings, affecting all future AI assistant decisions system-wide — hence medium severity.

From the tool's definition Elevate a project foundation to global scope... The foundation will be copied to ~/.decision-os with a GF- prefix.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

elevate_foundation Rate-limited

elevate_foundation 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.

View as policy code

policy.json

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

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Decision OS MCP, so you can run agents against it safely.

FAQ

Questions about elevate_foundation

What does the elevate_foundation tool do? +

Elevate a project foundation to global scope. Use when a project-specific learning has proven universal. The foundation will be copied to ~/.decision-os with a GF- prefix. Strong signal for elevation: - Foundation has confidence 2+ - Pattern has been validated across multiple implementations - Learning applies regardless of tech stack. It is categorised as a Write tool in the Decision OS 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 elevate_foundation? +

Register the Decision OS MCP server in PolicyLayer and add a rule for elevate_foundation: 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 Decision OS MCP. Nothing to install.

What risk level is elevate_foundation? +

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

Can I rate-limit elevate_foundation? +

Yes. Add a rate_limit block to the elevate_foundation 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 elevate_foundation completely? +

Set action: deny in the PolicyLayer policy for elevate_foundation. 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 elevate_foundation? +

elevate_foundation is provided by the Decision OS MCP server (marianstefi20/decision-os-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.