Score a creative prompt, script, or ad concept for hook strength, benefit clarity, product signal, call-to-action, channel fit, audience fit, and brand fit. This is a transparent heuristic, not a proprietary prediction model.
AI agents call score_creative to retrieve information from Raven without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
channel | string | — | Target channel. |
audience | string | — | Target audience if not in a brand profile. |
creative_text | string | Yes | Prompt, script, ad copy, or creative concept to score. |
brand_profile_id | string | — | Local Raven brand profile ID. |
Parameters from the server's own tool schema.
This tool retrieves and evaluates data against a set of design principles without creating, modifying, deleting, or executing external operations. It is purely analytic and read-only in nature. The low severity reflects that misuse would only produce unhelpful scoring feedback rather than causing system damage, data loss, or unintended side effects.
From the tool's definition Tool performs scoring and analysis of creative content using transparent heuristics. The description emphasizes evaluation against defined criteria (hook strength, benefit clarity, product signal, call-to-action, channel fit, audience fit, brand fit) with no…
Attacks that exploit this kind of access
Score a creative prompt, script, or ad concept for hook strength, benefit clarity, product signal, call-to-action, channel fit, audience fit, and brand fit. This is a transparent heuristic, not a proprietary prediction model. It is categorised as a Read tool in the Raven MCP Server, which means it retrieves data without modifying state.
score_creative accepts 4 parameters: channel, audience, creative_text, brand_profile_id. Required: creative_text. The full parameter table on this page comes from the server's own tool schema.
Register the Raven MCP server in PolicyLayer and add a rule for score_creative: 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 Raven. Nothing to install.
score_creative 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 score_creative 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 score_creative. 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.
score_creative is provided by the Raven MCP server (raven-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 →