MCP guide

https://mcp.mxaura.ai/mcp is a remote Model Context Protocol server. Point an MCP-capable assistant at it, sign in, and the assistant can read (and, with the right scopes, act on) your mxAURA account through 21 tools.

It speaks MCP protocol 2025-06-18 over streamable HTTP, authenticates with OAuth 2.1 (PKCE, dynamic client registration), and every call goes through the same public API as an API key would — same scopes, same rate limits, same tenant boundary.

Connect

Claude.ai (web / desktop app)

Settings → Connectors → Add custom connector → URL https://mcp.mxaura.ai/mcp → Connect. A browser window opens to auth.mxaura.ai; sign in to mxAURA, review the scopes, approve. Done.

Claude Code

claude mcp add --transport http mxaura https://mcp.mxaura.ai/mcp

then /mcp inside a session to authenticate.

Cursor / other MCP clients

Add a server of type "streamable HTTP" (or "remote") with the URL above. If the client cannot do OAuth itself, use the mcp-remote bridge:

{ "mcpServers": { "mxaura": { "command": "npx", "args": ["-y", "mcp-remote", "https://mcp.mxaura.ai/mcp"] } } }

What happens underneath

The client fetches https://mcp.mxaura.ai/.well-known/oauth-protected-resource and learns the authorization server is https://auth.mxaura.ai.
It reads https://auth.mxaura.ai/.well-known/oauth-authorization-server, registers itself at /register (RFC 7591), and opens /authorize with a PKCE S256 challenge.
You sign in to mxAURA (2FA if enabled) and approve the scopes shown.
The client exchanges the code at /token and gets an access token (mxa_oat_…, 1 hour) and a refresh token (30 days).

No secrets are typed anywhere. To disconnect, remove the connector in the client; its access token expires within the hour and cannot refresh. Removing an integration from mxAURA's side is on the roadmap.

Scopes and the `support` profile

A client that asks for no specific scopes gets the support profile:

components.read brandings.read pools.read campaigns.read flows.read
hubs.read articles.read identity.read dispatch.read

Every read, nothing that sends, publishes or spends. A client may request it by name (scope=support) or ask for specific scopes; the consent screen shows exactly what will be granted. tools/list only returns the tools the token can call, so an assistant never sees a tool it cannot use.

The tools

Tool	Scope	What it does
`get_me`	any	Who the token is: account, scopes
`list_components`, `get_component`	components.read	Messages, headers, summaries, signatures, senders, templates
`list_pools`, `get_pool`, `get_pool_messages`	pools.read	Pools and the ordered messages composed into them
`compose_message`	pools.write	Compose a message into a pool
`list_campaigns`, `get_campaign`	campaigns.read	Campaigns
`simulate_campaign`	campaigns.read	The full journey a contact would receive — read-only, the same engine dispatch uses
`list_flows`, `get_flow`	flows.read	Flows with enrollment counts
`enroll_contact`	enrollments.write	Enroll a HubSpot contact — sends real email, capped per hour
`get_dispatch_log`	dispatch.read	What was sent, to whom, with what result
`list_hubs`, `get_hub`, `get_hub_stats`	hubs.read	Hubs, their settings and embed details, 30-day traffic
`list_articles`, `get_article`	articles.read	Articles: metadata, status, placements, SEO, stats
`get_identity`	identity.read	The messaging identity (frameworks)
`list_brandings`	brandings.read	Brandings

Each tool's description and input schema are served by tools/list; the assistant reads them directly.

What the model can and cannot see

Bodies are never returned to the model. Message HTML, article markdown, layout templates, personal messages come back as their length (html_chars: 2140) instead of their text. Content a user wrote is untrusted input to a model: a hub article must never be able to instruct an assistant. A workflow that truly needs a body fetches it over the REST API.

Everything else — names, ids, statuses, positions, stats, reasons — comes back as structured JSON.

Limits

MCP calls are API calls. The token's burst (25 / 10 s), per-minute (120) and account (600 / min) limits apply, and the assistant is told when it hits one (rate_limited (HTTP 429): …) so it can back off rather than crash the session. Tool results are truncated at 100 KB.

Typical questions it can answer

"Why didn't Darren get Tuesday's email?" → get_dispatch_log, filter by contact; the entry says blocked / no_sender or filtered / ….
"What would this contact receive from the Q4 campaign?" → simulate_campaign.
"Which hub is the pricing article in, and is it live?" → get_article.
"How much traffic did the Insights hub get this month?" → get_hub_stats.
"What's our positioning?" → get_identity.

Troubleshooting

Symptom	Cause	Fix
Client says "unauthorized" after connecting	Access token expired and the client did not refresh	Reconnect; most clients refresh silently
A tool is missing	The token lacks its scope	Reconnect and approve the scope, or accept that `support` is read-only
`enroll_contact` returns `enrollment_cap`	Hourly cap reached	Wait for `Retry-After`
"server did not respond"	Network, or the client is using a stdio transport	Use a streamable-HTTP transport or `mcp-remote`

https://mcp.mxaura.ai/health reports the server and protocol version without authentication.