Metadata MCP Connector

Generate Brand Kit

generate_brand_kit

Analyze a company's brand from their website and extract brand identity. Fetch brand assets (logo, colors, fonts) and create a brand DNA document for consistent advertising.

                            ALSO KNOWN AS: analyze brand, get brand from website, extract brand identity, brand analysis, company branding, fetch brand, brand style guide

                            USE THIS TOOL WHEN USER WANTS TO:
                            - Analyze their brand from website
                            - Extract brand colors, logo, fonts
                            - Match their existing brand style
                            - Get brand identity for ads
                            - Create brand guidelines

                            COMMON USER PHRASES THAT NEED THIS TOOL:
                            - "match my brand"
                            - "my company website is [URL]"
                            - "analyze my brand"
                            - "get my brand colors"
                            - "brand style"
                            - "company branding"
                            - "use my brand"

                            WORKFLOW:
                            1. Call this tool with company domain
                            2. Returns brand DNA (colors, fonts, logo, style)
                            3. Use brand info in generate_brand_creative

                            PARAMETERS:
                            - domain: Company website URL (e.g., "dapta.ai", "example.com")
                            - brand_name: Optional brand name override
                            - force_regenerate: Set true to refresh existing brand kit

                            OUTPUT:
                            - Logo variations and usage guidelines
                            - Brand colors (primary, secondary, accent)
                            - Typography/fonts
                            - Messaging framework
                            - Channel-specific guidelines

                            IMPORTANT: Automatically checks if brand kit exists. Returns existing kit if found.

                            RETRY SCOPE: This tool handles ONE domain per call. When the user asks to retry or
                            regenerate the kit for specific named domain(s), call it ONLY for those domain(s),
                            with force_regenerate=true, starting with the domain the user named. NEVER widen the
                            request: domains the user did not name stay untouched, even if their kits were
                            generated together as a batch earlier in the conversation.

                            KEYWORDS: brand, website, URL, domain, logo, colors, fonts, identity, style, company, analyze, extract, branding, guidelines

Input Schema

TableJSON Schema

Name	Required	Description
`domain`	Yes	Company website URL or domain
`brand_name`	No	Optional brand name override
`sample_ad_urls`	No	Optional ad image URLs to analyze (max 5)
`force_regenerate`	No	If True, regenerate brand kit even if one already exists. Default: False

Schema Changelog

Changes observed during successful MCP inspections.

First observedSep 16, 2026

TDQS

A3.8/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses useful behavioral traits beyond annotations: it automatically checks for an existing brand kit and returns it, supports force_regenerate to refresh, and handles exactly one domain per call. Annotations already indicate readOnly=false and destructiveHint=false, so the description adds helpful operational detail about cache behavior and retry safety.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with headings and front-loaded purpose, but it is unnecessarily long. The 'ALSO KNOWN AS', 'COMMON USER PHRASES', and 'KEYWORDS' sections heavily overlap and repeat the same intent, making the description bloated. It would be stronger if trimmed to the core workflow, output, and retry guidance.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema present, the description compensates with an OUTPUT section listing logo variations, colors, typography, messaging framework, and channel-specific guidelines. It also explains the single-domain behavior, existing-kit check, force_regenerate, and downstream use with generate_brand_creative. Minor gap: sample_ad_urls isn't explained in the narrative, but the schema covers it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description's PARAMETERS section mostly restates the schema (domain, brand_name, force_regenerate) and adds a domain example, but it omits sample_ad_urls entirely. The schema already covers parameter meaning, so the description adds limited extra value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states a specific action ('Analyze a company's brand from their website and extract brand identity') and names the produced artifact (brand DNA document, brand kit). It also lists concrete use cases and common user phrases. However, it doesn't explicitly distinguish itself from the sibling get_brand_kit, especially since the description notes it returns an existing kit when found.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit 'USE THIS TOOL WHEN USER WANTS TO' and 'COMMON USER PHRASES' sections, plus a detailed RETRY SCOPE with clear instructions about which domains to regenerate and a 'NEVER widen the request' warning. It lacks an explicit 'when not to use this tool' or direct alternative routing (e.g., get_brand_kit), so it doesn't fully earn a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Metadata MCP Connector tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?