# TeamMeet (remote · teammeet.ai)

Start meetings and work with meeting transcripts, notes, recordings and follow-up tasks.

- Trust score: 63/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `teammeet.ai`: 63/100 (this document), [markdown](https://verifymcp.io/servers/theguysaccount-teammeet/teammeet.md), [page](https://verifymcp.io/servers/theguysaccount-teammeet/teammeet)

## Channel facts

- Endpoint: `https://teammeet.ai/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 18 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 70/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1878 tokens (~104/item across 18 items; 18 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 17/100
  - Stability observed for 5 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 89/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 68% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 3 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "send_message" implies "send" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 18 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the TeamMeet MCP server?

TeamMeet is a hosted endpoint at https://teammeet.ai/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http theguysaccount-teammeet 'https://teammeet.ai/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "theguysaccount-teammeet": {
      "url": "https://teammeet.ai/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "theguysaccount-teammeet": {
      "type": "http",
      "url": "https://teammeet.ai/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.theguysaccount-teammeet]
url = "https://teammeet.ai/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "theguysaccount-teammeet": {
      "type": "remote",
      "url": "https://teammeet.ai/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add theguysaccount-teammeet --url 'https://teammeet.ai/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  theguysaccount-teammeet:
    url: "https://teammeet.ai/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "theguysaccount-teammeet": {
      "Transport": "http",
      "Url": "https://teammeet.ai/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add theguysaccount-teammeet -t streamable-http -u 'https://teammeet.ai/mcp'
```

### Other

```json
{
  "mcpServers": {
    "theguysaccount-teammeet": {
      "type": "http",
      "url": "https://teammeet.ai/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-04 (score 63, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 62, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-01 (score 61, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-31 (score 61)

First indexed and scored.

## MCP tools (18)

### `start_meeting` (~151 tokens)

Start a new meeting and get its code and link. The link works in any browser with no account and no download. Nobody can join a meeting that was not started this way.

Input parameters:

- `mode` (string): What the AI in the room should do with what is said. "meet" keeps live notes; "agenda" tracks topics you supply; "brainstorm" draws pictures from the conversation; "align" runs a decision protocol; "…
- `topics` (array): Agenda topics, if mode is agenda.

### `list_meetings` (~29 tokens)

List the meetings this key started that are still running, with how many people are in each.

### `get_transcript` (~87 tokens)

The full transcript of a meeting, with who said each line. Speaker attribution here is not a guess from a mixed audio stream — each microphone is transcribed separately, so the name on a line is the connection the words arrived on.

Input parameters:

- `meeting` (string, required): The meeting code, like abc-defg-hij.
- `since` (number): Only lines after this epoch-ms timestamp.

### `get_notes` (~63 tokens)

What the room has read out of the conversation so far — decisions, open questions, actions and live disagreements. Every item carries a verbatim quote from the transcript; anything that failed that check is marked unverified rather than presented as fact.

Input parameters:

- `meeting` (string, required)

### `send_message` (~46 tokens)

Post a message into the meeting chat, from this agent, under its own name. Everyone in the room sees it.

Input parameters:

- `meeting` (string, required)
- `text` (string, required)

### `speak` (~78 tokens)

Say something out loud in the meeting. It is spoken through the room's speakers and joins the transcript, so it is on the record like anything else that was said. Use sparingly — this interrupts people.

Input parameters:

- `meeting` (string, required)
- `text` (string, required): Keep it to a sentence or two. Nobody wants to be read a paragraph.

### `draw` (~59 tokens)

Generate a picture from a description and put it in the meeting for everyone to see.

Input parameters:

- `kind` (string): diagram and infographic render legible labels; visual and meme are for imagery.
- `meeting` (string, required)
- `prompt` (string, required)

### `list_recordings` (~31 tokens)

Recordings this key can see, newest first, with their share links.

Input parameters:

- `meeting` (string)

### `send_feedback` (~200 tokens)

File something you noticed about Team Meet — a bug, a confusing moment, an idea. It goes on the list the product is built from; repeats are counted and move the item up. Be specific: the page, what you expected, what happened. Set fix=true when the person wants the platform itself changed: it becomes a fix request, an AI engineer turns it into a pull request, and a person reviews it before it ships. The reply carries a link to follow it.

Input parameters:

- `actual` (string)
- `expected` (string)
- `fix` (boolean): true = the person wants this FIXED in the platform; it becomes a pull request.
- `kind` (string)
- `page` (string): The URL or path where you noticed it.
- `severity` (integer): 5 = blocks the task, 1 = polish
- `text` (string, required): What you noticed, in one or a few sentences.

### `submit_fix` (~207 tokens)

Open a pull request against Team Meet: a unified diff (`git diff` output) you wrote against its source, for a fix request. Give feedback_id to attach it to an existing request (see send_feedback, or GET /api/fixes for the open ones), or give text to file the request and attach the fix in one step. Nothing is applied automatically — a person reviews and merges. Run the tests your change touches first (AGENTS.md says which) and report them.

Input parameters:

- `body` (string): What changed and why, and how you checked it.
- `diff` (string, required): Unified diff against the source, with diff --git headers.
- `feedback_id` (string): The fix request this resolves.
- `page` (string)
- `tests` (object)
- `text` (string): If there is no feedback_id: what is being fixed, as a person would report it.
- `title` (string): One line, like a commit subject.

### `import_transcript` (~195 tokens)

Bring a meeting transcript or a chat log from another tool into the dashboard of the account this key was minted by — .vtt/.srt captions (Zoom, Google Meet, Teams, Fireflies, Grain), Otter-style text, Read AI JSON, any JSON list of turns with names and times, or the chats: Google Meet's chat log, Zoom's meeting_saved_chat.txt, a WhatsApp export. Speaker labels are kept exactly as written; a chat is filed as a chat. Returns the meeting id and link.

Input parameters:

- `name` (string, required): The file name, with its extension — it says what format this is and often carries the date.
- `started_at` (string): ISO 8601 start time, if the file does not say.
- `text` (string, required): The whole file as text.
- `title` (string): A title for the meeting, if the file name is not one.

### `send_notetaker` (~145 tokens)

Send the TeamMeet notetaker to a Zoom, Google Meet, Microsoft Teams or Webex meeting you did not host. It joins as a participant, records, and when the call ends the transcript, recap and action items land in the dashboard of the account this key was minted by. Needs a key minted while signed in. Metered in minutes per month by plan.

Input parameters:

- `join_at` (string): ISO 8601 time to join, for a meeting later today. Omit to join now.
- `name` (string): What the bot is called in the call. Default "TeamMeet notetaker".
- `url` (string, required): The meeting link.

### `my_tasks` (~73 tokens)

What your calls have handed to you — the person this TeamMeet connector belongs to — to do: who asked, what they asked for, which call, and where each one has got to. Open ones first. Use get_task for the whole of one.

Input parameters:

- `all` (boolean): Include finished and declined ones too.

### `get_task` (~72 tokens)

One task handed to you from a call, in full: the words the person asked in, who they are, the lines of the call just before (each with the microphone it came in on), and any TeamMeet fix request it is about.

Input parameters:

- `task` (string, required): The task id, tmt_…

### `update_task` (~113 tokens)

Say where a task has got to. The call it came from sees it in its chat: "working" when you start, "done" with a short note and the link to what you made (a pull request, a document), or "blocked" with what you need from a person.

Input parameters:

- `links` (array): Links to what you made.
- `note` (string): Two plain sentences at most.
- `status` (string, required)
- `task` (string, required): The task id, tmt_…

### `join_meeting` (~97 tokens)

Join a TeamMeet call you are in, as your own agent — "<your name>'s Claude" appears in the call, announced in its chat, and anyone in it can remove you. Then call listen to hear it. You can only join a call the person this connector belongs to is in (signed in) or started.

Input parameters:

- `meeting` (string, required): The meeting code, like abc-defg-hij, or its link.

### `listen` (~144 tokens)

Wait for what happens next in a call you joined: new transcript lines with who said each (ground truth — every microphone is transcribed on its own), new chat messages, and tasks handed to you. Returns as soon as there is something, or after wait_seconds. Pass back the "next" value as since. Keep calling it to stay in the call; you leave after 90 seconds without one.

Input parameters:

- `meeting` (string, required)
- `since` (number): The "next" value from the last listen. Omit for the last few minutes.
- `wait_seconds` (number): How long to wait for something new, up to 45. Default 25.

### `hand_off` (~88 tokens)

Hand a task to another person's agent, from the call you are in — they see it in the call and send it to their Claude with one press. Name the person as they appear in the call.

Input parameters:

- `meeting` (string, required)
- `task` (string, required): What their agent should do, in plain words.
- `to` (string, required): The person's name as it shows in the call.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/theguysaccount-teammeet/teammeet#diagnostics

## Score history

- 2026-11-05: 63
- 2026-11-04: 63
- 2026-11-03: 62
- 2026-11-02: 62
- 2026-11-01: 61
- 2026-10-31: 61

## Common questions

### What is the TeamMeet MCP server?

TeamMeet is an MCP server listed in the public MCP registry as io.github.theguysaccount/teammeet. Start meetings and work with meeting transcripts, notes, recordings and follow-up tasks. This page covers its hosted endpoint (https://teammeet.ai/mcp).

### Is the TeamMeet MCP server safe to use?

TeamMeet scores 63 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the TeamMeet MCP server expose?

TeamMeet exposes 18 tools: start_meeting, list_meetings, get_transcript, get_notes, send_message, and 13 more. Their descriptions and schemas cost roughly 1,878 tokens of context every time the server is loaded.

### Does the TeamMeet MCP server require authentication?

No. We connected to TeamMeet without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the TeamMeet MCP server still maintained?

TeamMeet is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://teammeet.ai/mcp
- Authorisation metadata: https://teammeet.ai/.well-known/oauth-protected-resource/mcp
- Repository: https://github.com/theguysaccount/mcp-catalog
- Website: https://teammeet.ai/
- Changelog RSS feed: https://verifymcp.io/servers/theguysaccount-teammeet/teammeet.xml
- Changelog JSON feed: https://verifymcp.io/servers/theguysaccount-teammeet/teammeet.json
- HTML version of this page: https://verifymcp.io/servers/theguysaccount-teammeet/teammeet