Choose your path

Choose where to start.

Create a Brand Context Protocol from your existing material, or return to a brand you already manage. You review the result before anything is published.

Add Encoded Brands from the connector directory

Add Encoded Brands from the connector directory. If it is not listed, add https://encoder.encodedbrands.ai/api/agent/mcp as a custom connector.

On Team or Enterprise plans, an owner may need to allow it.

In ChatGPT, open its app or connector settings. Look for an option to create an MCP app or add a custom connector. Your plan or workspace admin may hide it.

If that option is missing, choose the guided Encoder. You can connect your tools later.

An Encoded Brands site.

Connecting your assistant to your brand context.

There are two ways an assistant can read a published BCP.

Custom MCP connector.

Encoded's Registry exposes a public, read-only MCP endpoint bound to your handle. In ChatGPT, Claude, and Grok you can add it as a custom remote connector, subject to your plan, workspace, and administrator settings. The assistant can then request your root file and the specific sections a task needs. Public reads need no credentials and cost nothing. This is a connection you configure. It is not native adoption or endorsement by those vendors.

Pasted URL.

You can paste the Registry or self-hosted URL into a chat. That gives the assistant a place to fetch from in that conversation. It does not install anything, does not persist, and does not confirm the assistant read every file.

Using it well.

Ask for the sections the task needs: voice for wording, claims and boundaries for factual statements, visual and representation for images and people. If an assistant says it read a file it never retrieved, that is the assistant's error, not a property of the file.

Connector setup steps change with vendor releases. Use each vendor's current documentation rather than a copied click-path.