brand_get
Read one brand in full: its four sections, its personas, its files and its ad accounts. An agent reads it before it acts for the brand.
Ask for work that needs a brand. The agent reads the brand in full before it writes or judges anything.
“Write three ad headlines for Acme.”
The agent calls brand_get for Acme. It reads the voice and the guidelines, and it sees the personas, the files and the attached ad accounts. You then get headlines in the voice of Acme, not generic headlines.
The job guide Describe a brand shows each step of the job.
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). |
Output
A successful call returns this object in structuredContent.
| Field | Type | Always present | Description |
|---|---|---|---|
advertisers |
array of object | yes | The ad accounts attached to the brand. |
advertisers[].advertiserId |
string | yes | The ad account (acc_…). |
advertisers[].createdAt |
number | yes | Milliseconds since the Unix epoch, in UTC. |
advertisers[].provider |
string | yes | The provider of the ad account, such as meta. AdCrunch reads it from the ad account. |
advertisers[].targetId |
string | yes | The id of the brand that the ad account is attached to. |
advertisers[].targetType |
string | yes | The kind of record that the ad account is attached to: brand. |
brand |
object | yes | The brand in full. |
brand.createdAt |
number | yes | Milliseconds since the Unix epoch, in UTC. |
brand.createdBy |
string | yes | The user who created the record (usr_…). |
brand.description |
string | yes | One line about the brand. An agent picks a brand on it. |
brand.guidelines |
string or null | yes | The rules: claims to avoid, guardrails and compliance notes. Markdown. null when the section is not written. |
brand.id |
string | yes | The id of the brand (brd_…). |
brand.identity |
string or null | yes | Who the brand is: positioning, mission, offer, category. Markdown. null when the section is not written. |
brand.logoDocumentId |
string or null | yes | The document that the brand nominates as its logo (doc_…). null when no document is the logo. |
brand.messaging |
string or null | yes | Key messages, value propositions and proof points. Markdown. null when the section is not written. |
brand.name |
string | yes | The display name. |
brand.revision |
number | yes | The version of the record. Each change adds 1. Send it as base_revision to update or delete the record. |
brand.slug |
string | yes | The handle of the brand in the organization. The tools take it as brand_name. |
brand.updatedAt |
number or null | yes | Milliseconds since the Unix epoch, in UTC. null until the first change. |
brand.voice |
string or null | yes | The tone of voice and the personality. Markdown. null when the section is not written. |
brand.websiteUrl |
string or null | yes | The public site of the brand. null when it is not set. AdCrunch keeps the address and does not read the site. |
documents |
array of object | yes | The finalized files of the brand, each with its URL. The content of a file is not in the bundle. |
documents[].createdAt |
number | yes | Milliseconds since the Unix epoch, in UTC. |
documents[].filename |
string | yes | The name of the file at upload. |
documents[].id |
string | yes | The id of the document (doc_…). |
documents[].mimeType |
string | yes | The media type of the stored file. AdCrunch reads it from the file at finalize. |
documents[].name |
string | yes | The display name. It is the filename until someone renames it. |
documents[].sizeBytes |
number | yes | The size of the stored file, in bytes. AdCrunch reads it from the file at finalize. |
documents[].targetId |
string | yes | The id of the brand that holds the document (brd_…). |
documents[].targetType |
string | yes | The kind of record that holds the document: brand. |
documents[].url |
string | yes | The public URL of the file. Each person who has the URL can read the file. |
personas |
array of object | yes | The personas of the brand, newest first, with no prose. |
personas[].ageMax |
integer, 0 to 120 or null | yes | The highest age of the audience. null when the range has no upper bound. |
personas[].ageMin |
integer, 0 to 120 or null | yes | The lowest age of the audience. null when the range has no lower bound. |
personas[].description |
string | yes | One line about the persona. An agent picks a persona on it. |
personas[].name |
string | yes | The display name. |
personas[].slug |
string | yes | The handle of the persona. It is unique in its brand, not in the organization. The tools take it as persona_name. |
personas[].sections |
object | yes | Which of the four sections of the persona hold text. Read the text with persona_get. |
personas[].sections.frictions |
boolean | yes | true when the section frictions holds text. |
personas[].sections.language |
boolean | yes | true when the section language holds text. |
personas[].sections.motivations |
boolean | yes | true when the section motivations holds text. |
personas[].sections.profile |
boolean | yes | true when the section profile holds text. |
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_foundforbiddeninvalid_requestinternal_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.
Example
The arguments:
{
"brand_name": "acme"
}
The result, in structuredContent:
{
"advertisers": [
{
"advertiserId": "acc_1203456789012345",
"createdAt": 1790000000000,
"provider": "meta",
"targetId": "brd_6a9c33",
"targetType": "brand"
}
],
"brand": {
"createdAt": 1790000000000,
"createdBy": "usr_4d8b12",
"description": "Running shoes sold direct to the runner, made to last a thousand kilometres.",
"guidelines": "- Name the distance, never the \"journey\".\n- Claim the kilometres the shoe is tested to, and no more.\n- Do not compare the shoe to a named competitor.",
"identity": "Acme makes one running shoe and sells it direct. The promise is a thousand kilometres on the same pair, and a resole rather than a replacement.",
"messaging": "- One shoe, a thousand kilometres.\n- Resole it twice, and keep running on it.\n- Sold direct, so the price is the cost of the shoe.",
"voice": "Plain and measured. Short sentences. No superlative the shoe cannot earn.",
"id": "brd_6a9c33",
"logoDocumentId": "doc_7d1f58",
"name": "Acme",
"revision": 4,
"slug": "acme",
"updatedAt": 1790086400000,
"websiteUrl": "https://acme.example"
},
"documents": [
{
"createdAt": 1790086400000,
"filename": "acme-logo.png",
"id": "doc_7d1f58",
"mimeType": "image/png",
"name": "acme-logo.png",
"sizeBytes": 48213,
"targetId": "brd_6a9c33",
"targetType": "brand",
"url": "https://documents.adcrunch.dev/org_3a7f10/doc_7d1f58"
},
{
"createdAt": 1790000000000,
"filename": "acme-brand-guidelines.pdf",
"id": "doc_5e2b41",
"mimeType": "application/pdf",
"name": "acme-brand-guidelines.pdf",
"sizeBytes": 1482064,
"targetId": "brd_6a9c33",
"targetType": "brand",
"url": "https://documents.adcrunch.dev/org_3a7f10/doc_5e2b41"
}
],
"personas": [
{
"ageMax": 45,
"ageMin": 28,
"description": "Runners who already own a pair, and who buy the next one without looking at another brand.",
"name": "Loyalists",
"sections": {
"frictions": true,
"language": true,
"motivations": true,
"profile": true
},
"slug": "loyalists"
}
]
}