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.
This record as markdown: /tools/dev-futur-panda-laguarde/propose-preference.md
What propose_preference does on Laguarde
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.
Why propose_preference is rated Medium
Creates or modifies reusable preference proposals; reversible human review required before acceptance.
From the tool's definition Capture developer feedback, add to proposal, create new proposal.
Attacks that exploit this kind of access
The rule that runs propose_preference safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Laguarde, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For propose_preference, this is the rule to start with:
propose_preference 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Laguarde, apply this rule, and every propose_preference call is checked against it from then on.
Questions about 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. It is categorised as a Write tool in the Laguarde MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Laguarde MCP server in PolicyLayer and add a rule for propose_preference: 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 Laguarde. Nothing to install.
propose_preference 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 propose_preference 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 propose_preference. 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.
propose_preference is provided by the Laguarde MCP server (laguarde-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Laguarde, and thousands of servers like it.
This server
Across the catalogue