Atlas / MCP servers / vexa-ai / Vexa

VexaBLOCK

Name: Vexa
Author: vexa-ai

mcp/vexa-ai/vexa

MCP server by vexa-ai · api · claude code · codex · Audited 2026-09-22

Open-source meeting transcription API for Google Meet, Microsoft Teams & Zoom. Auto-join bots, real-time WebSocket transcripts, MCP server for AI agents. Self-host or use hosted SaaS.

Verdict

BLOCK

Grade

Trust score

27 /100

Exposed tools

—

Transport

streamable-http

License

Apache-2.0

Stars

2,809

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

Open-source meeting bots and real-time transcription — cloud or fully self-hosted.

A bot joins your Google Meet, Microsoft Teams, and Zoom calls and streams speaker-attributed transcripts in real time — through our API or one you host — then feeds sandboxed agents that build a Markdown knowledge base your team owns. Apache-2.0, air-gap-ready. (Jitsi: join + capture offline-proven, live validation pending — #883.)

[](LICENSE) [](#️-status--roadmap) [](#-quickstart) [](https://discord.gg/Ga9duGkVz9)

[vexa.ai](https://vexa.ai) runs Vexa 0.12 for meeting bots and transcription. Sandboxed knowledge agents are self-hosted only — self-host Vexa to run the full stack.

[Connect your agent](https://vexa.ai/connect?utm_source=github&utm_medium=readme) · [Get an API key](https://vexa.ai/start?utm_source=github&utm_medium=readme) · [Talk to the founder](https://cal.com/dmitrygrankin/web)

Why Vexa

Every meeting-AI tool you can buy sends your conversations to their cloud and rents you access back. Vexa inverts that: run the stack yourself, point it at your own models, own what your meetings become.

No one else has all three:

*Vexa is in the meeting.* A real bot joins Meet, Teams and Zoom — Jitsi offline-proven, live

validation pending — and streams speaker-attributed transcripts live. That bot fleet is the genuinely hard part — every "chat with your docs" tool starts after a transcript exists. Vexa produces it.

Your knowledge is files you own. Meetings compile into

Read from source at commit 245ce1792c3eOBSERVED · 2026-09-22

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.

claude-code

claude mcp add transcript-rendering --env ADMIN_API_TOKEN=${ADMIN_API_TOKEN} --env ADMIN_TOKEN=${ADMIN_TOKEN} --env ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY} --env ANTHROPIC_AUTH_TOKEN=${ANTHROPIC_AUTH_TOKEN} -- npx -y @vexaai/[email protected]

claude-desktop

{
  "mcpServers": {
    "transcript-rendering": {
      "command": "npx",
      "args": [
        "-y",
        "@vexaai/[email protected]"
      ],
      "env": {
        "ADMIN_API_TOKEN": "${ADMIN_API_TOKEN}",
        "ADMIN_TOKEN": "${ADMIN_TOKEN}",
        "ANTHROPIC_API_KEY": "${ANTHROPIC_API_KEY}",
        "ANTHROPIC_AUTH_TOKEN": "${ANTHROPIC_AUTH_TOKEN}"
      }
    }
  }
}

Trust audit

BLOCKgrade F · trust 27/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.

Layer	What it checks	Result
L0	Provenance & inventory	WARN
L1	Static analysis of the code	FAIL
L2	Instruction surface (what it tells the agent)	WARN
L3	Class-specific surface	PASS
L4	Behavioural (sandbox)	SKIPPED

What the source does

Filesystem: declared (10 observation(s))
Network: declared (13 observation(s))
Shell: declared (6 observation(s))
Dependencies: not all pinned
Secrets in source: found

Findings (25)

HIGHCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95

clients/terminal/src/canvas/runtime.tsx:64

const fn = new Function(

Why it matters. evaluates text as code

Fix. remove; use a parser or a dispatch table

MEDIUMInventory / provenance · inv.binary · CWE-1104

core/meetings/modules/zoom-capture/src/zoom-chat.ts

zoom-chat.ts

Why it matters. a compiled or binary member cannot be reviewed from source

Fix. ship source, or explain the binary in the README

MEDIUMCode injection · code.dynamic_import · CWE-78, CWE-94, CWE-95

core/flows/src/flows_defs/production.py:557

mod = importlib.import_module(name)

MEDIUMCode injection · code.dynamic_import · CWE-78, CWE-94, CWE-95

core/meetings/services/meeting-api/src/meeting_api/__init__.py:47

return importlib.import_module(f"{__name__}.{name}")

MEDIUMInformation disclosure · disclose.log_secret · CWE-209, CWE-532

core/identity/src/identity_core/secrets.py:46

`repr`/`str` are redacted so an accidental `logger.info(secret)` or f-string leaks nothing.

MEDIUMInformation disclosure · disclose.log_secret · CWE-209, CWE-532

core/meetings/services/transcription/src/transcription/main.py:148

logger.warning(f"Invalid or missing API token - X-API-Key: {api_key is not None}, Authorization: {bool(auth_header)}")

MEDIUMNetwork egress · net.beacon_words · CWE-200, CWE-319

core/meetings/services/meeting-api/src/meeting_api/bot_spawn/invocation.py:215

callback_url: Optional[str] = None,

MEDIUMNetwork egress · net.beacon_words · CWE-200, CWE-319

core/meetings/services/meeting-api/src/meeting_api/bot_spawn/invocation.py:235

if callback_url:

MEDIUMNetwork egress · net.beacon_words · CWE-200, CWE-319

core/meetings/services/meeting-api/src/meeting_api/bot_spawn/invocation.py:236

spec["callbackUrl"] = callback_url

MEDIUMNetwork egress · net.beacon_words · CWE-200, CWE-319

core/meetings/services/meeting-api/src/meeting_api/bot_spawn/service.py:799

callback_url=f"{meeting_api_url}/runtime/callback",

MEDIUMNetwork egress · net.raw_ip · CWE-200, CWE-319

clients/slim/vexa_slim/config.py:11

DEFAULT_GATEWAY = "http://127.0.0.1:18056"