MCP · Agent-native · Apache 2.0

Claude MCP
Meeting
Transcription

Connect Claude Desktop, ChatGPT, or any MCP-compatible agent to live meeting transcription. Your agent can drop a bot into a meeting, stream transcripts, and act on what's being said — all via MCP tools.

No credit card required
Starred by 2k+ developers on GitHub
vexa · live transcript
LIVE

Waiting for meeting participants…

Connected · Google Meet
Teams
Meet
Vexa
🦀
Real-time Meeting Data for AI

Feed meetings into your AI. Live.

AI needs data, and the best data is real-time. Vexa streams transcripts, audio, and context from any meeting straight to your models and agents — as it happens.

Built for MCP-native agents

Vexa is the only Apache-2.0 meeting transcription API that ships as an MCP server. Add one entry to your Claude Desktop config (or any MCP-compatible host) and your agent gets a `vexa.create_bot` tool, a `vexa.get_transcript` tool, and live access to what's happening in any Google Meet, Microsoft Teams, or Zoom call. Build agents that join meetings on your behalf, summarize as they go, draft follow-ups in real time, and trigger CRM / Slack / Linear actions when the transcript matches a rule.

  • Native MCP server — one config line in Claude Desktop, ChatGPT, or any MCP host
  • Tools include create_bot, get_transcript, list_meetings — agents read live meeting context
  • Same Apache 2.0 license: run the MCP server alongside your self-hosted Vexa for full data residency
Add Vexa to Claude Desktop — ~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "vexa": {
      "command": "npx",
      "args": ["-y", "@vexa-ai/mcp-server"],
      "env": {
        "VEXA_API_KEY": "your-key-here",
        "VEXA_API_BASE": "https://api.cloud.vexa.ai"
      }
    }
  }
}

# Then in Claude:
#   "Drop a bot into https://meet.google.com/abc-defg-hij,
#    summarize the conversation every 5 minutes, and flag
#    any mention of pricing or renewal."

Set $API_BASE to https://api.cloud.vexa.ai (hosted) or http://localhost:8056 (self-host). Get $API_KEY from /get-started.

Claude MCP integration FAQ

What agent builders ask before they wire Vexa into Claude / ChatGPT / custom MCP hosts.

What MCP hosts does this work with?

Any MCP-compatible client — Claude Desktop, Claude.ai (via remote MCP), ChatGPT (via its MCP-compatible flow), Continue.dev, and any custom agent built with the official MCP SDK. The Vexa MCP server is a standard stdio MCP server.

What tools does the MCP server expose?

create_bot (drop a bot into a meeting URL), get_transcript (fetch transcript chunks for a meeting), list_meetings (recent meetings + status), and delete_bot (end a bot session early). The full schema is in the MCP integration doc.

Can my agent act on transcript chunks in real time?

Yes. The pattern: agent calls create_bot, polls get_transcript every few seconds (or subscribes to a webhook the agent's host exposes), reasons about the latest chunks, and triggers its own tools (Slack message, CRM update, follow-up email) when the transcript matches a rule.

How is this different from giving Claude a generic transcription API?

Two things. (1) MCP gives the agent a typed tool surface — Claude understands the shape of meetings and transcripts natively, no prompt-engineering the API. (2) It works with the platform mix you actually use: drop bots into Meet, Teams, AND Zoom from the same conversation, without rewriting auth flows for each.

Does the MCP server work with self-hosted Vexa?

Yes — set VEXA_API_BASE to your self-hosted gateway URL. The MCP server is a thin layer over the same REST API; pointing it at a self-hosted instance gives you fully on-prem agent-to-meeting access.

Common patterns

What developers build with Vexa MCP

Three agent shapes we see repeatedly across MCP + Vexa builders.

01Pattern 1

Real-time meeting summarizer agent

Scenario

You want an agent that joins your meetings, summarizes them every 5 minutes, and posts the running summary to a Slack channel — without you running a separate script.

What you get

In Claude: "drop a bot into <URL>, summarize every 5 minutes, post to #sales-calls". Claude orchestrates the bot, reads transcripts, summarizes, and uses its Slack tool to post. Stop the bot with a single prompt.

02Pattern 2

CRM-enrichment agent triggered by calendar

Scenario

You want an agent that watches your calendar, joins customer calls automatically, transcribes them, and updates the CRM record with action items + sentiment.

What you get

Custom MCP agent: Calendar tool + Vexa tool + HubSpot tool. Calendar trigger → Vexa create_bot → get_transcript loop → reason over chunks → HubSpot update. Build it once in your agent host, run forever.

03Pattern 3

Sales-coaching agent reviewing recordings

Scenario

Sales managers want an agent that reviews every rep's calls and writes a coaching note pointing at specific transcript moments.

What you get

Agent runs get_transcript on completed meetings, finds discovery questions / objections / next steps, and writes a structured coaching review back to your tool of choice (Notion, Linear, Slack DM).

Quickstart

Connect Claude to live meetings in 5 minutes

Add one MCP server entry to Claude Desktop. Your agent gets create_bot, get_transcript, and list_meetings tools immediately.

  1. 1

    Get a Vexa API key

    Sign up at vexa.ai/get-started or mint a key locally on your self-hosted gateway.

  2. 2

    Install the Vexa MCP server

    Add the JSON snippet on the right to your Claude Desktop config (or equivalent for ChatGPT / Continue).

  3. 3

    Restart your MCP host

    Restart Claude Desktop. The vexa tools (create_bot, get_transcript, list_meetings) appear in the tool list.

  4. 4

    Try it

    Ask Claude: "Drop a bot into <Meet/Teams/Zoom URL> and summarize what they discuss." The agent calls create_bot, then polls get_transcript.

  5. 5

    Build the agent

    Compose vexa tools with your other MCP tools (Slack, Notion, Linear, CRM) to build a meeting-aware agent in your stack.

How it works under the hood

MCP architecture

Vexa MCP server is a thin stdio MCP server that wraps the Vexa REST API. Your MCP host (Claude Desktop, ChatGPT, custom agent) spawns the server as a subprocess; tool calls round-trip to Vexa over HTTPS (or HTTP to a self-hosted gateway). No audio data passes through the MCP host — it stays in the Vexa pipeline (bot pod → Whisper → transcript store).

Pipeline

bot pod audio capture whisper-svc transcript chunks REST / WebSocket
Pricing

Pay only for
what you use

Self-host for free, or let us run it for you. Simple usage-based pricing—no per-seat tax.

Free
$0

Apache 2.0 · Self-host forever

Best for teams who need full control

View on GitHub
Full platform — no limits
Your infrastructure, your data
Google Meet + Teams + Zoom
Docker Compose / K8s deploy
REST API + WebSockets + Dashboard
Community support
Individual
$12/mo

1 bot · Flat monthly · Everything included

Best for personal use — 1 meeting at a time

No credit card required

1 concurrent bot
Google Meet + Teams + Zoom
Real-time transcription included
Audio capture + webhooks
12-month audio storage
REST API + WebSockets + Dashboard
Pay-as-you-go
$0.30/hr

Bot infrastructure · +$0.20/hr transcription

Best for teams & API builders · $5 free credit

No credit card required

Unlimited bots
Google Meet + Teams + Zoom
Transcription add-on: +$0.20/hr
Audio capture + webhooks
12-month audio storage
REST API + WebSockets + Dashboard
Enterprise

On-premises, OpenShift, Kubernetes. Dedicated support + SLA.

Book a call
Transcription API

For self-hosted Vexa bot users. Transcription only — $0.002/min.

Get started
Bot: Vexa $0.30/hr vs Recall.ai $0.50/hr —40% cheaper

Frequently asked questions

What's included in the $0.30/hr Bot Service?

The base rate covers bot infrastructure: audio capture, webhooks, and 12 months of audio storage across Google Meet, Microsoft Teams, and Zoom. Add real-time transcription for +$0.20/hr ($0.50/hr total).

Which plan is right for me?

Choose Individual ($12/mo) if you need one bot for personal use—it includes real-time transcription, storage, and the Dashboard. Choose Pay-as-you-go ($0.30/hr) if you need multiple simultaneous bots or want to pay only for what you use—ideal for teams and API integrations. Both plans include Google Meet and Microsoft Teams support. Self-host for free from GitHub if you need full data control.

How does the free credit work?

Every new account gets $5 in free bot credit—no credit card required. That covers ~16 hours of bot time at $0.30/hr. All features are available: audio capture, transcription, real-time data, and full API access.

Can I self-host Vexa?

Yes. Vexa is Apache 2.0 licensed and fully self-hostable. Deploy with Docker Compose, Kubernetes, or OpenShift on your own infrastructure with complete data sovereignty.

How does Vexa compare to Recall.ai?

Vexa is open source, self-hostable, and up to 40% cheaper. Bot: $0.30/hr vs Recall.ai ~$0.50/hr. Transcription add-on: $0.20/hr vs ~$0.15/hr. See our detailed comparison.

What's the Individual plan for?

The Individual plan ($12/mo) is for single users who need one concurrent bot with unlimited meetings. It includes real-time transcription, recording, storage, REST API, WebSockets, and the UI Dashboard—everything you need for personal meeting intelligence. It supports Google Meet and Microsoft Teams, with Zoom coming soon.

Ready when you are

Connect your agent.
Live meeting context in 5 minutes.

No credit card, no SDK install — just an MCP server entry. Add it to Claude Desktop, restart, ask your agent to drop a bot into a meeting.

Apache 2.0 · Self-host or cloud · No credit card required