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.
Waiting for meeting participants…
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
{
"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.
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.
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.
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
Get a Vexa API key
Sign up at vexa.ai/get-started or mint a key locally on your self-hosted gateway.
- 2
Install the Vexa MCP server
Add the JSON snippet on the right to your Claude Desktop config (or equivalent for ChatGPT / Continue).
- 3
Restart your MCP host
Restart Claude Desktop. The vexa tools (create_bot, get_transcript, list_meetings) appear in the tool list.
- 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
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
Documentation
Go deeper on MCP
Tool schemas, transcript chunk format, interactive-bot extensions, self-host setup.
MCP integration guide
Install, configure, and use the Vexa MCP server with Claude Desktop and other MCP hosts.
Interactive bots
Turn the Vexa bot into an interactive participant — speak, chat, share visuals from your agent.
Bots API reference
The underlying REST API the MCP server wraps.
Transcripts API
get_transcript tool internals — chunk format, polling cadence, language detection.
Authentication
Scope agent access to a single meeting, or to your whole tenant.
Self-host deployment
Run both the MCP server and Vexa fully in your VPC for sovereign agent stacks.
Full reference at docs.vexa.ai.
Related reading
Keep going on MCP
Tutorials, deep-dives, and adjacent surfaces from across the Vexa substrate.
Claude Desktop MCP setup — real-time Google Meet transcripts
The canonical tutorial: add Vexa MCP to Claude Desktop, ask Claude mid-meeting.
Coaching & call review use case
Build an MCP-powered coaching agent that scores calls in real time.
n8n integration
Same goal (orchestration over Vexa) via n8n if your stack already lives there.
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.
Apache 2.0 · Self-host forever
Best for teams who need full control
1 bot · Flat monthly · Everything included
Best for personal use — 1 meeting at a time
No credit card required
Bot infrastructure · +$0.20/hr transcription
Best for teams & API builders · $5 free credit
No credit card required
On-premises, OpenShift, Kubernetes. Dedicated support + SLA.
For self-hosted Vexa bot users. Transcription only — $0.002/min.
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