Brandfetch for AI agents
Brandfetch is an API that marketers and developers use to pull a company's logo, colors, and other brand assets for consistent use across apps. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.
What agents do in Brandfetch.
Look up a company's brand assets
Read-only pull of a company's logo, colors, and fonts by domain before using them in a design.
Search for a brand by name
Search Brandfetch's index for a brand when only a company name, not a domain, is known.
Check webhook subscriptions
List the webhooks configured on the account before adding a new one for brand update alerts.
7 Brandfetch actions, graded by risk.
Every Brandfetch action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
7Look things up. Allowed by default.
- brandfetch.get_taxonomyGet Brandfetch Taxonomy
- brandfetch.list_webhooksList Webhooks
- brandfetch.search_brandsSearch Brands
- brandfetch.get_brand_infoGet Brand Information
- brandfetch.get_graphql_versionGet GraphQL API Version
- brandfetch.get_transaction_infoGet Transaction Info
- brandfetch.list_subscribable_eventsList Subscribable Events
write
0Create and change things. Allow, or ask the user first.
- No write actions.
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Brandfetch in three steps.
- 01Your users connect BrandfetchThey add their Brandfetch api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “updates” can wait for the user to approve.
- 03Any agent can actYour agent calls Brandfetch through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('brandfetch', { read: 'allow', write: 'ask', destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Brandfetch connects.
Users add their Brandfetch api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
The same Brandfetch connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →
- AUTH
- API key
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use Brandfetch from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Brandfetch and Arc0, answered.
Can I use Brandfetch with Claude, ChatGPT or Cursor?
Yes. Connect Brandfetch to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Brandfetch actions you allow.
How do users connect Brandfetch?
Users add their Brandfetch api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
Which Brandfetch actions can my agent take?
7 in total: 7 read, 0 write and 0 destructive. Your policies decide which of them each agent may call.
Can I make my agent read-only in Brandfetch?
Yes. Allow read actions and deny writes in the Brandfetch policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Brandfetch too?
Yes. The same Brandfetch connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Brandfetch into your agent.
Your users connect Brandfetch once, under your brand. Your agent gets 7 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan