MeetStream

npx add-mcp 'https://mcp.meetstream.ai/mcp'

MeetStream MCP Server

Give Claude - or any MCP-compatible client - direct access to the MeetStream meeting-bot API. Add one URL, sign in, and your assistant can run the full bot lifecycle (create, record, transcribe, summarize, interact live, manage calendar auto-join) through 19 tools.

https://mcp.meetstream.ai/mcp

MeetStream hosts the server. There is nothing to install or run on your machine, and it is always the current version.

Quick start

1. Add https://mcp.meetstream.ai/mcp to your AI tool. Do not add a key.
2. Click Connect (in Claude Code: run /mcp, then choose Authenticate). Your browser opens app.meetstream.ai.
3. Sign in to MeetStream, then click Allow. MeetStream creates an API key for this connection. You do not see or copy the key.
4. Ask your AI tool: "list my meetstream bots". A list, or an empty list, means that you are connected.

The exact steps for each tool are in Connect.

Which URL to use

URL	Use it for
https://mcp.meetstream.ai/mcp	All current clients. Streamable HTTP. The replies stream as server-sent events (SSE), so you do not need a separate SSE setting.
https://mcp.meetstream.ai/sse	Only clients that support just the older HTTP+SSE transport (2024-11-05). The sign-in and the API key work the same way.

Your AI tool ──HTTPS + OAuth sign-in──► mcp.meetstream.ai ──► api.meetstream.ai

The old npm package @meetstream/mcp (npx @meetstream/mcp) is frozen at 0.3.0 and no longer maintained. It predates the current create_bot defaults and fixes. Use the hosted URL instead.

---

Connect

Add the URL with no key. Your client finds MeetStream's sign-in, opens app.meetstream.ai in your browser, and you click Allow. The dashboard creates an API key for that connection, named MCP · <app name> · <date> · <number>. To disconnect, delete that key on the API keys page.

This is the page that opens in your browser. If you are not signed in to MeetStream, you sign in first, then you see this page:

The page shows the name of the app that asked to connect. If you do not recognize the app, click Cancel. The sign-in link is valid for 15 minutes.

Claude Code

claude mcp add --transport http meetstream https://mcp.meetstream.ai/mcp
# then run /mcp in Claude Code and choose Authenticate

Claude (web and desktop)

Customize → Connectors → + → Add custom connector. Name it meetstream, set the URL to https://mcp.meetstream.ai/mcp, leave the OAuth fields blank, and click Connect.

Cursor

~/.cursor/mcp.json (or install the MeetStream Cursor plugin), then click Connect next to meetstream in Cursor Settings → MCP:

{
  "mcpServers": {
    "meetstream": { "url": "https://mcp.meetstream.ai/mcp" }
  }
}

VS Code

.vscode/mcp.json, then start the server and sign in when VS Code asks:

{
  "servers": {
    "meetstream": { "type": "http", "url": "https://mcp.meetstream.ai/mcp" }
  }
}

Windsurf

~/.codeium/windsurf/mcp_config.json. Cascade asks you to sign in on first use. If your Windsurf version cannot finish the sign-in, use an API key header (below):

{
  "mcpServers": {
    "meetstream": { "serverUrl": "https://mcp.meetstream.ai/mcp" }
  }
}

Codex

~/.codex/config.toml, then run codex mcp login meetstream:

[mcp_servers.meetstream]
url = "https://mcp.meetstream.ai/mcp"

Any other MCP client

Point it at https://mcp.meetstream.ai/mcp as a remote (Streamable HTTP) server. Clients that support MCP authorization sign in by themselves: protected resource metadata (RFC 9728), authorization server metadata (RFC 8414), dynamic client registration (RFC 7591) and the authorization code flow with PKCE. Access tokens last an hour and refresh automatically.

Or use an API key

For clients without OAuth, or for scripts and CI, create a key at app.meetstream.ai/api-keys and send it as a header:

{
  "mcpServers": {
    "meetstream": {
      "url": "https://mcp.meetstream.ai/mcp",
      "headers": { "Authorization": "Bearer ms_YOUR_API_KEY" }
    }
  }
}

• Claude Code: claude mcp add --transport http meetstream https://mcp.meetstream.ai/mcp --header "Authorization: Bearer $MEETSTREAM_API_KEY"
• Codex: add bearer_token_env_var = "MEETSTREAM_API_KEY" to the [mcp_servers.meetstream] block.
• X-MeetStream-Api-Key: <key> works too. For connector UIs that cannot set headers, https://mcp.meetstream.ai/mcp?key=<key>. The server never logs query strings, but a key in a URL can end up in client-side history, so prefer OAuth or a header.

Older clients (HTTP+SSE)

/mcp is the main endpoint, and its replies already stream as server-sent events (text/event-stream). Clients that only speak the older 2024-11-05 HTTP+SSE transport connect to https://mcp.meetstream.ai/sse with the same sign-in or key options. The stream's first event names the per-session message endpoint; the key never appears in it.

Check it is connected

Ask your client something like "list my meetstream bots" - if it returns data (or a clean empty list) instead of an error, you are connected.

---

Then just ask

"Join my standup at https://meet.google.com/abc-defg-hij, record it with Deepgram transcription, and give me the transcript when it's done."

"List my bots from today and give me the AI summary of the 3pm customer call."

"Send 'we'll follow up by email' into the meeting the bot is in, then show them our logo."

"Schedule a bot for tomorrow's board meeting on my calendar."

---

Full capability list - 19 tools

Bot lifecycle

Tool	What it does
create_bot	Sends (or schedules, via join_at) a bot to a Zoom / Google Meet / Microsoft Teams meeting. Audio only by default; record_video turns video on and records it in speaker view unless video_layout: "grid_view" is asked for, and per-participant video stays off unless requested. Configurable: transcription provider + language, callback_url for webhooks, video recording, per-participant audio/video streams, MIA conversational agent, signed-in joins (google_login_domain / teams_login_domain, optional sign_in_email / strict_email, for domains already registered on your account), authenticated Zoom joins (zoom_zak_url / zoom_obf_url), custom attributes, retention window, idempotency key (safe retries - a repeat call returns the original bot, never a duplicate). Returns bot_id and transcript_id (when a provider is set).
list_bots	Lists every bot on the account (paginated).
get_bot_status	Current lifecycle status - one of Joining, InWaitingRoom, InMeeting, Recording, Leaving, Stopped, NotAllowed, Denied, Error, Done.
get_bot_detail	Full session metadata: platform, timings, status timeline, the canonical transcript_id, caption_file (for the meeting_captions provider), and the original request payload.
get_bot_summary	MeetStream's built-in AI meeting summary - no external LLM call needed.
remove_bot	Makes the bot leave an active meeting immediately. Recorded data is kept.
delete_bot_data	Permanently deletes a bot's audio, video, and transcripts. Requires confirm: true - only call this when the user has explicitly asked to delete data. Irreversible.

Transcription

Tool	What it does
get_transcript	Fetches a transcript by bot_id. Automatically resolves the transcript_id (it is never delivered in webhooks) via /detail → /transcriptions. Set wait: true to poll until it's ready; raw: true for unprocessed provider output. Segments come back as { speaker, transcript, start_time, end_time }.
list_transcriptions	Lists every transcription run for a bot - provider, status, and presigned download URLs (valid 1h).
transcribe_audio	(Re-)transcribes a bot's recorded audio with a chosen provider - useful to retry with a different provider or language after the meeting.

Media & meeting data

Tool	What it does
get_media_urls	Presigned URLs for audio (1h), video (10min), audio_streams/video_streams (per-participant - needs separate_audio_streams/separate_video_streams at creation), or screenshots.
get_participants	Everyone detected in the meeting - display name, full name, status, stream ids.
get_chats	In-meeting chat messages captured during the call.
get_speaker_timeline	Who spoke and when, as a timeline of speaker segments.

Live meeting interaction

Tool	What it does
send_chat_message	Posts a chat message into the live meeting through the bot.
send_image	Displays an image or GIF as the bot's video frame. img_url must be publicly accessible (no base64).

Calendar

Tool	What it does
list_calendar_events	Upcoming events from a connected Google Calendar. (Connecting a calendar - POST /calendar/create_calendar with OAuth credentials - is a one-time setup usually done via the MeetStream CLI or dashboard.)
schedule_calendar_bot	Schedules (action: "schedule") or removes ("unschedule") a bot for a specific calendar event.

Reference

Tool	What it does
webhook_events_guide	Returns the webhook reference - envelope shape (event and bot_event), the two-layer bot.stopped terminal model, status codes, and streaming-provider caveats, checked against captured production deliveries. Have your model call this before it writes any webhook handler code.

---

What makes this different from just reading the docs

Every tool description and the webhook_events_guide bake in live-verified ground truth, confirmed against real production bot runs, that the public API docs currently get wrong:

• Every delivery carries event, and most also carry bot_event with the specific name. Read event to route, bot_event for detail.
• Terminals are two-layer: every ending arrives once with event: "bot.stopped", and bot_event says why (bot.stopped, bot.kicked, bot.notallowed, bot.denied, bot.failed). Lobby timeouts, denials and failures carry status_code: 500. Branch on bot_event, not bot_status - a kick and a clean exit both report Stopped.
• Streaming-only transcription providers (deepgram_streaming, assemblyai_streaming, jigsawstack_streaming, meetstream_streaming, meeting_captions) produce no post-call transcript, so transcription.processed never fires. bot.done still does. A post-call transcript fetch for them returns 202 indefinitely, so cap your polling.
• transcript_id is never in a webhook payload - get_transcript resolves it for you automatically instead of making the model guess.
• Safe defaults everywhere: automatic_leave timeouts on every create_bot call, and recording_permission_denied_timeout floored at 60 (the API rejects lower values with a 400).

How it works

The server holds no API key of its own: each request (or SSE session) carries the caller's key or an OAuth token that wraps it. A request with no credentials gets a 401 with setup instructions and a WWW-Authenticate header pointing OAuth clients at the sign-in flow. Streamable HTTP is stateless, so the service scales horizontally with no shared state; OAuth tokens are encrypted, self-contained values, so there is no token database either.

MeetStream runs the server; it is written in Go and its source is not published. This repo holds the user docs and the MCP Registry entry (server.json). To report a problem, open an issue here.

Troubleshooting

Symptom	Fix
Sign-in page says the link has expired	Sign-in links last 15 minutes. Start the connection again from your client
401 from mcp.meetstream.ai	Sign in through your client (OAuth), or send Authorization: Bearer <key> / X-MeetStream-Api-Key - the server has no key of its own
Tool call returns a 401 from the API	The key is invalid or revoked (for OAuth connections, the key named after the app was deleted). Reconnect, or generate a new key at app.meetstream.ai/api-keys
get_transcript returns ready: false	The meeting hasn't finished processing yet, or (for streaming providers) there is no post-call transcript - check get_bot_status first
Calendar tools return empty/errors	No calendar is connected yet - connect one via meetstream calendar connect in the CLI first
Your client only supports the old SSE transport	Use https://mcp.meetstream.ai/sse

---

Prefer a terminal? See the MeetStream CLI. Docs: docs.meetstream.ai · API spec: openapi.json · Migrating from Recall.ai: @meetstream/migrate

Privacy and telemetry

The hosted server records anonymous counts of which tools are called and whether each call succeeded. It never records your API key, OAuth tokens, meeting URLs, transcripts, or any other content. Server logs contain the request path only, never the query string.

MIT © MeetStream.ai