MCP servers · vexa-ai

Vexa: open-source meeting bots and real-time transcription

An open-source service whose bots join Google Meet, Microsoft Teams, Zoom and Jitsi calls to stream speaker-attributed transcripts, hosted or self-hosted.

This text was machine-translated from the publisher's own information and has not been checked by a human editor. The publisher's original text is the reference.

This resource was imported automatically from the sources listed below and has not been reviewed by the AI Gate team yet. The description is the publisher's own, as published. Check the repository before installing.

What it does

Vexa sends bots into video meetings on Google Meet, Microsoft Teams, Zoom and Jitsi. They stream speaker-attributed transcripts in real time through an API, which can be the hosted service or a deployment the user runs. Sandboxed agents can then turn the captured meetings into a Markdown knowledge base stored in a git repository. The project is licensed under Apache-2.0 and can run air-gapped.

It suits teams that want to keep meeting content on infrastructure they control, whether they need only a transcription API or want agents to work over their captured meetings. The agent runtime starts each agent in its own isolated, ephemeral container, and supports Docker, plain processes or Kubernetes as the backend.

The hosted service needs an account and an API key, and new accounts receive free bot credit without a card. Self-hosting runs in containers and needs Docker engine 26 or later. Transcription needs a token or a self-hosted GPU unit, because bot creation fails with 503 when speech-to-text is missing unless capture-only mode is set explicitly. Ubuntu 24.04 is the stated production target, and the agent plane is available only when self-hosted.

Limitations and requirements

Agents run only on a self-hosted deployment and are not part of the hosted service. Transcription requires a free token or a self-hosted GPU transcription unit; without it, bot creation returns 503 unless capture-only mode is enabled. Self-hosting requires Docker engine 26 or later. Building from source needs 8 vCPUs and 16 GB RAM. Ubuntu 24.04 is the stated production target. Jitsi support has been validated offline only; live validation is pending.

Safety

Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.

  • Runs code or changes an assistant's behaviour

Sources

  • Cline MCP Marketplace first seen 13 Nov 2026 · last seen 18 Nov 2026 · its page on the source
    2,965
    As shown on cline.bot when we last read it
MCP servers
hashicorp

Terraform MCP Server (HashiCorp)

HashiCorp's MCP server that gives an assistant current Terraform Registry information on providers, modules and policies, and can manage HCP Terraform workspaces.

1.6K GitHub starsCloud & DevOpsSoftware development
Updated 17 Nov 2026
MCP servers
modelcontextprotocol

MCP reference servers

Seven small example servers maintained by the Model Context Protocol project: files, Git, web fetching, memory, time, step-by-step thinking and a test server.

92K GitHub starsSoftware development
Updated 18 Nov 2026
MCP servers
redis

Redis MCP Server

Redis's official MCP server that lets an AI assistant store, read and search data in a Redis database, including streams, JSON documents and vector indexes.

642 GitHub starsData & databasesSoftware development
Updated 17 Nov 2026
MCP servers
firecrawl

Firecrawl MCP Server (web search and scraping)

Firecrawl's MCP server that lets an AI assistant search the web, turn pages and PDFs into clean Markdown, crawl sites and interact with dynamic pages.

7.8K GitHub starsWeb, search & browserProductivity & automation
Updated 17 Nov 2026
Vexa: open-source meeting bots and real-time transcription | AI Gate Discover