Skip to content
MeetStream MCP Server

MeetStream MCP Server

by MeetStream AI
Released
6 views
v0.3.0
MIT
Repository Docs npm
Developer ToolsProductivity

Summary

Send a bot into a Zoom, Google Meet or Teams call from your agent: 19 tools covering the bot lifecycle, transcripts, per-participant media, live chat and calendar scheduling.

Features

  • 19 tools covering the full meeting bot lifecycle across Zoom, Google Meet, Teams and Webex
  • Transcripts, per-participant media URLs, participant lists and a speaker timeline
  • Live in-meeting actions: send chat messages and images while the call is running
  • Calendar listing and scheduled bot dispatch
  • Hosted remote server at mcp.meetstream.ai — no install required
  • One-line Claude Code setup; works with Claude Desktop, Cursor, Windsurf and any MCP client

Installation

Set up this MCP server in your favorite AI agent — copy a ready-made configuration below.

Any MCP-compatible agent

Most agents (Claude, Cursor, Windsurf, VS Code, and more) read a standard mcpServers configuration.

  1. Open your agent's MCP configuration file.
  2. Merge the snippet below into it, filling in the environment variables with your own values.
  3. Restart the agent — the "MeetStream MCP Server" tools will be available.
{
  "mcpServers": {
    "meetstream-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@meetstream/mcp"
      ],
      "env": {
        "MEETSTREAM_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

Description

MeetStream's meeting bot API puts a recording, streaming and speaking bot into Zoom, Google Meet, Microsoft Teams and Webex calls. This is the official MCP server for it, which means an agent can run the whole meeting lifecycle — dispatch a bot, watch it join, pull the transcript afterwards — without you writing a line of HTTP glue.

The 19 tools

Bot lifecycle — create_bot, list_bots, get_bot_status, get_bot_detail, get_bot_summary, remove_bot, delete_bot_data.

Transcription — get_transcript, list_transcriptions, transcribe_audio.

Meeting data and media — get_media_urls, get_participants, get_chats, get_speaker_timeline. The speaker timeline is the one that makes agent summaries genuinely useful: attribution by participant rather than an undifferentiated wall of text.

Live interaction — send_chat_message and send_image, so the bot can act in the meeting while it is still running rather than only reporting on it afterwards.

Calendar — list_calendar_events, schedule_calendar_bot, plus a webhook_events_guide reference tool for wiring up lifecycle callbacks.

Running it

Local via npx -y @meetstream/mcp with a MEETSTREAM_API_KEY, or hosted at https://mcp.meetstream.ai/mcp?key=... with nothing to install. Claude Code users can add it in one line: claude mcp add meetstream --env MEETSTREAM_API_KEY=... -- npx -y @meetstream/mcp. Cursor, Windsurf and any other MCP client work the same way. Keys are minted at app.meetstream.ai/api-key.

Worth knowing

Bots are billed by the hour ($0.35, prorated to the second, with $5 of free credit to start), so an agent holding this server can spend money by leaving a bot in an empty room — get_bot_status and remove_bot exist for a reason. And putting a recording bot into someone else's meeting is a consent question in most jurisdictions before it is a technical one; disclose accordingly.

Covered in the Weekly

Related MCP Servers

MCP: Headroom

by Headroom Labs

New

Context-compression MCP server that shrinks tool outputs, logs, files and RAG chunks before they reach the model, cutting 60-95% of tokens on JSON payloads.

Developer Tools
2 views

MCP: Engram

by Gentleman Programming

New

Persistent memory for coding agents as a single Go binary — SQLite and FTS5 behind MCP, an HTTP API, a CLI and a TUI, with no Node, Python or Docker required.

Developer Tools
2 views

MCP: agent-device

by Callstack

New

Give a coding agent a live feedback loop on real mobile, TV and desktop apps — inspect, tap, type and capture evidence on iOS, Android and HarmonyOS over MCP or a CLI.

Developer Tools
3 views

MCP: Weights & Biases MCP Server

by Weights & Biases

New

The official W&B MCP server: query experiment runs, Weave LLM traces, artifacts and registries in natural language, and write findings back as a W&B report.

Developer Tools
3 views
Browse all MCP servers →