# propose_preference

Capture reusable developer feedback. Add to an existing proposal when it expresses the same preference; otherwise create a new proposal. Three observations promote it for human review, but only a human can accept it.

Agent View of the PolicyLayer registry record for `propose_preference`. HTML page: https://policylayer.com/tools/dev-futur-panda-laguarde/propose-preference

## Facts

- Tool: `propose_preference`
- Server: Laguarde (`laguarde-mcp`) — https://policylayer.com/tools/dev-futur-panda-laguarde.md
- Install: `npx -y laguarde-mcp`
- Homepage: https://github.com/FuturPanda/laguarde
- Risk category: Write (Medium risk)
- Registry record: grade B, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "propose_preference",
    "arguments": {}
  }
}
```

## Why propose_preference is rated Medium

Creates or modifies reusable preference proposals; reversible human review required before acceptance.

From the tool's own definition: "Capture developer feedback, add to proposal, create new proposal."

## Use case

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

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Laguarde:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "propose_preference": {
      "limits": [
        {
          "counter": "propose_preference_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Laguarde (4)

- `evaluate_action` — Read — https://policylayer.com/tools/dev-futur-panda-laguarde/evaluate-action.md
- `get_policy_bundle` — Read — https://policylayer.com/tools/dev-futur-panda-laguarde/get-policy-bundle.md
- `list_preference_proposals` — Read — https://policylayer.com/tools/dev-futur-panda-laguarde/list-preference-proposals.md
- `record_decision` — Read — https://policylayer.com/tools/dev-futur-panda-laguarde/record-decision.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=dev-futur-panda-laguarde · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/dev-futur-panda-laguarde