Docs / MCP
Brandloop MCP documentation
Brandloop exposes a limited remote MCP endpoint for controlled testing with an out-of-band Brandloop API key. Its stdio server is an internal preview. Neither path is a one-click ChatGPT or verified Claude integration.
What MCP is for
The curated MCP surface maps scoped Brandloop operations for brand sources, assets, generation profiles, and generation jobs. It does not expose billing, admin, provider-secret, or destructive tools.
Distribution boundary
The stdio server is an internal preview with no public package or supported customer installation path. The remote Streamable HTTP endpoint is limited: it accepts a Brandloop API key configured out of band and does not implement OAuth 2.1, dynamic client registration, or a consent flow. Mutating tools accept an optional idempotencyKey; when it is omitted, the server derives a deterministic key from the complete normalized tool input so identical retries remain safe.
- Claude compatibility needs client-auth and tool-call verification.
- ChatGPT is blocked until OAuth 2.1 and developer-mode validation exist.
- A durable Brandloop agent runtime is planned, not implemented.
Agent safety
MCP clients should preserve approval gates, workspace scope, and API-key limits. They should not bypass Brandloop review, billing, channel, or provider controls.
- Use Brandloop scopes and account boundaries.
- Keep generated work reviewable.
- Do not expose provider secrets to MCP clients.
Curated MCP tools
| Tool | Access | What it does |
|---|---|---|
| brand_source_submit | Write | Submit a public brand source URL (website or social profile) for Brandloop to fetch and analyze |
| brand_source_get | Read | Fetch a previously submitted brand source by id |
| asset_list | Read | List Brandloop media assets scoped to the API key's account and workspace |
| asset_upload | Write | Create a Brandloop asset upload session and return a short-lived signed upload instruction |
| asset_upload_complete | Write | Verify a previously created Brandloop asset upload and mark it uploaded or ready |
| asset_get | Read | Fetch a Brandloop media asset by id, including a short-lived signed download URL when one is available |
| generation_profiles_list | Read | List Brandloop-owned generation profile aliases available to this API key |
| generation_create | Write | Start a Brandloop media generation job for a selected Brandloop workflow |
| generation_get | Read | Fetch a Brandloop media generation job by id |
List available remote tools
httpThe remote endpoint uses the configured Brandloop API key; it is not an anonymous discovery endpoint.
POST /api/mcp HTTP/1.1
Host: brandloop.app
Authorization: Bearer $BRANDLOOP_API_KEY
Accept: application/json, text/event-stream
Content-Type: application/json
{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}Limitations and boundaries
- MCP is not a claim of universal unattended publishing.
- MCP clients do not receive raw generation, channel, billing, or storage provider credentials.
- Remote MCP uses an out-of-band Brandloop API key. It is not OAuth 2.1 and is not a supported one-click ChatGPT or verified Claude connector.
Common questions
- Is MCP live for every agent client?
- No. Remote MCP is limited, the stdio package is an internal preview, Claude needs verification, and ChatGPT is blocked on OAuth 2.1 plus client validation.
- Can MCP skip content approval?
- No. Brandloop's public positioning keeps human review and workspace controls in the loop.