Vexa is an open-source meeting transcription system whose bots join Google Meet, Microsoft Teams, and Zoom calls and stream speaker-labeled transcripts through an API. It is for teams that want meeting transcription and downstream knowledge processing either through hosted services or by running the stack themselves. The catalogue entries provide agents and instructions for working with Vexa.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/Vexa-ai/vexaWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/vexa-ai/vexa/claude-plugin)<a href="https://agentmods.dev/plugins/vexa-ai/vexa/claude-plugin"><img src="https://agentmods.dev/badge/plugins/vexa-ai/vexa/claude-plugin/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/vexa-ai/vexa/claude-plugin"><img src="https://agentmods.dev/badge/plugins/vexa-ai/vexa/claude-plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
vexa scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"name": "vexa",
"displayName": "Vexa",
"version": "0.1.0",
"description": "Send a bot to a Google Meet, Teams or Zoom call and read the transcript, live or after, with speakers labelled. Hosted at api.cloud.vexa.ai, or point it at your own self-hosted Vexa.",
"author": { "name": "Vexa", "url": "https://github.com/Vexa-ai" },
"homepage": "https://docs.vexa.ai/vexa-mcp",
"repository": "https://github.com/Vexa-ai/vexa",
"license": "Apache-2.0",
"keywords": ["meetings", "transcription", "google-meet", "microsoft-teams", "zoom", "meeting-bot", "mcp"],
"userConfig": {
"vexa_api_key": {
"type": "string",
"title": "Vexa API key",
"description": "From https://vexa.ai/account (hosted) or printed by `make all` on a self-hosted stack. Or open https://vexa.ai/connect and paste the prompt into Claude Code instead of installing this plugin.",
"sensitive": true,
"required": true
},
"vexa_mcp_url": {
"type": "string",
"title": "Vexa MCP URL",
"description": "Hosted: https://api.cloud.vexa.ai/mcp. Self-hosted: your gateway's /mcp, e.g. http://localhost:18056/mcp.",
"default": "https://api.cloud.vexa.ai/mcp",
"required": false
}
},
"mcpServers": {
"vexa": {
"type": "http",
"url": "${user_config.vexa_mcp_url}",
"headers": { "Authorization": "Bearer ${user_config.vexa_api_key}" }
}
}
}
What it installs
The manifest is a name and a version. 2 skills travel with it, and installing the plugin installs all of them — 140 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 35 lines scan A e73db4663557
vexa is a plugin published in the GitHub repository Vexa-ai/vexa (2,907 stars, last pushed today), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-07.
Other plugins, from other repositories
join-meeting
Join video meetings (Google Meet, Zoom, Teams) as an AI bot with voice, avatar, screenshare, and real-time transcription. Any AI agent can participate in calls via voice conversation, TTS, and meeting intelligence.
agentcall
Let your AI agent join Google Meet, Zoom, or Microsoft Teams as a speaking, listening, presenting participant — works with Claude Code, Codex, Gemini CLI, and 30+ other agents.
daodan
One command per intention, with no parameters: initialize, onboard, check health, brainstorm, investigate, build, fix, refactor, continue, finish, sync, review, map, document, presentation, workbook, theme, verify, tidy. Each command is a thin entry into the canonical method of its owner, usable alone or as a step of…
obw
Obsidian Workspace — project-scoped vault productivity (capture / notes / PM). Skills own folder layout and templates; /obw:pm splits a spec into blocking tickets; /issue is a Claude Mod pane that lists a view of the project's dashboard, draws Mermaid as text diagrams, and can open a card in the browser through viz.…
misticos
Standing rules and drift reminders.
interview
Deep requirements gathering skill that interviews users through thoughtful, in-depth questions before implementation. Extracts technical, UX, architectural, and edge case requirements.