Suggest a fireplace based on a vibe, mood, or use case described in plain English. Matches against tags, mood text, and palette. Returns the top 3 recommendations. Args: - vibe: free-form description of what you want (e.g.
AI agents call fireplace_recommend to retrieve information from Digital Fireplace without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and filters data from a static collection of pixel-art fireplaces based on mood/tag matching. It has no side effects, cannot modify state, and poses no security risk beyond potentially returning recommendations. It is purely a Read operation—data retrieval with no blast radius if misused by an AI agent.
From the tool's definition Tool description states it 'Suggest[s] a fireplace' and 'Returns the top 3 recommendations' based on user input. No modification, deletion, or execution of external operations occurs—it only queries and returns data matching the provided vibe description.
Attacks that exploit this kind of access
Suggest a fireplace based on a vibe, mood, or use case described in plain English. Matches against tags, mood text, and palette. Returns the top 3 recommendations. Args: - vibe: free-form description of what you want (e.g. It is categorised as a Read tool in the Digital Fireplace MCP Server, which means it retrieves data without modifying state.
Register the Digital Fireplace MCP server in PolicyLayer and add a rule for fireplace_recommend: 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 Digital Fireplace. Nothing to install.
fireplace_recommend 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 fireplace_recommend 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 fireplace_recommend. 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.
fireplace_recommend is provided by the Digital Fireplace MCP server (mhoydich/digital-fireplace-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →