Log in

Integrations › OpenAI-compatible & custom

Integration

Connect an OpenAI-compatible or custom agent.

MeetCrew fronts any OpenAI-compatible chat-completions endpoint — Microsoft Azure OpenAI, a compatibility-layer host, or a local model — or your own custom webhook that implements the MeetCrew agent contract. Bring your own key; MeetCrew supplies presence, voice, memory, and disclosure.

How it fits

Any backend that answers.

If your agent isn’t a Microsoft backend, MeetCrew still fronts it — over the standard OpenAI chat-completions interface, or a webhook you control.

OpenAI-compatible endpoints

Any endpoint that implements the OpenAI chat-completions API — Microsoft Azure OpenAI, a compatibility layer, or a local model. Bind it and authenticate with an API key; MeetCrew’s tools are offered through the standard tools parameter.

Custom webhook

Supply an HTTPS endpoint that implements the MeetCrew agent contract. Requests are authenticated with an HMAC signature keyed by a per-deployment shared secret.

Memory back over MCP

However your agent is hosted, it reads MeetCrew’s structured meeting memory back over an MCP server or API and acts on it.

Connect it

Bind a custom backend in a few steps.

  1. On the teammate’s Backend binding step, choose OpenAI-compatible or Custom webhook.
  2. Supply the endpoint and its credential — an API key, or an HMAC shared secret for a webhook.
  3. MeetCrew calls your endpoint with the meeting context and speaks the reply; an empty reply produces silence, not an invented answer.
  4. Invite the teammate. It joins disclosed and answers in the room.

API keys and webhook secrets are stored as Azure Key Vault secret references — never raw secrets. You bring your own model key; MeetCrew is not the model provider.

Bring the agent you already run.

Start a pilot and we’ll front your OpenAI-compatible or custom endpoint in a real meeting.