Skip to content
AdCrunch
Esc
↑↓navigate↵open⌘Jpreview
On this page

brand_get

Fetch one brand by slug — its identity, voice, guidelines, messaging and personas — so an agent knows who it is acting for.

Fetches a single Brand by its slug: the full brand context plus the current revision. Discover slugs first with brand_list.

This is what an agent reads before writing copy, judging a campaign, or making a recommendation — so that it sounds like you rather than like a generic assistant.

Input

Field Type Required Description
brand_name string yes The Brand slug (its per-organization handle).

Output

{ brand, personas, documents, advertisers }.

The brand carries logoDocumentId when one of its documents has been nominated as the logo — fetch it with document_get to see the image itself.

It also carries websiteUrl when one has been set: the brand’s public site. Useful for exactly what the sections do not cover — if the brief is thin on something you need, that is where to look.

The brand carries slug, name, description, revision, and four context sections:

Section What belongs in it
identity Positioning, mission, what you offer, category
voice Tone and personality — how the brand sounds
guidelines Do’s and don’ts, guardrails, claims to avoid
messaging Key messages, value propositions, proof points

Each section is free-form markdown, and each is independently optional — a section you haven’t written yet is null, which is normal rather than an error.

Example

“Write three ad headlines for Acme Running.”

brand_get({ brand_name: 'acme-running' });
// → { brand: { slug: 'acme-running', voice: 'Direct, unfussy, never hype.',
//              websiteUrl: 'https://acme.example', … },
//     personas: [{ slug: 'marathon-maya', ageMin: 30, ageMax: 44, … }],
//     documents: [], advertisers: [] }

The agent reads voice and guidelines before drafting, so the headlines come back on-brand instead of generic.

Requires the brand:read scope.

Reference

Fetch a single brand by its slug: the full brand context (identity, voice, guidelines, messaging), its websiteUrl if one is set, plus its personas (summaries only — who the brand talks to), its documents (each with a URL) and the ad accounts attached to it. Unwritten sections are null — read the website yourself for anything they do not cover. Load a persona’s own context with persona_get. Echo the revision back as base_revision when updating.

Input

Argument Type Required Description
brand_name string yes The brand slug (its stable per-organization handle).

Failure codes

A failed call has isError set, and structuredContent.error holds one of these codes. Errors describes the shape of a failed call.

  • not_found
  • forbidden
  • invalid_request
  • internal_error

Scope

The token must hold brand:read. Auth & scopes lists each scope.

Annotations

A client reads these hints. A hint that the tool does not declare has the default value of the MCP specification.

  • Read-only. The tool changes nothing.
  • Closed world. The tool reads and writes the data of AdCrunch only.

Was this page helpful?