// SCAN REPORT

Attendee MCP Server

11 tools. 7 can modify or destroy data without limits.

2 destructive tools with no built-in limits. Policy required.

Last updated: 12 Jun 2026

7 can modify or destroy data

4 read-only

11 tools total

Community server · catalogue entry verified 12/06/2026

How to control Attendee MCP Server ↓

TOOL MAP

What Attendee MCP Server exposes to your agents

Read (4) Write / Execute (5) Destructive / Financial (2)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Attendee MCP Server tools

Destructive · High delete_bot_data This tool irreversibly deletes data (recordings, transcripts, and other bot-associated information) and cannot be undone. Destructive · High remove_meeting_bot Removing a bot from a meeting destroys its active session and cannot be undone without re-creating the bot. Execute · High create_meeting_bot This tool initiates an external agent action: deploying a bot into a live meeting, which has real-world side effects including joining a call uninvited, recording participants (potential privacy/legal implications), and Execute · Medium make_bot_speak This tool triggers an active external operation — causing a bot to audibly speak in a live meeting via text-to-speech.

7 of Attendee MCP Server's 11 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Attendee MCP Server

PolicyLayer is an MCP gateway — it sits between your AI agents and Attendee MCP Server, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "delete_bot_data": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "send_chat_message": {
    "limits": [
      {
        "counter": "send_chat_message_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_bot_status": {
    "limits": [
      {
        "counter": "get_bot_status_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Attendee MCP Server — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON ATTENDEE →

Free to start. No card required.

FULL CATALOGUE

All 11 Attendee MCP Server tools

DESTRUCTIVE 2 tools

Destructive delete_bot_data Delete all data associated with a bot (recordings, transcripts, etc.) Destructive remove_meeting_bot Remove a bot from a meeting

EXECUTE 3 tools

Execute create_meeting_bot Create a bot to join a meeting and record/transcribe it Execute make_bot_speak Make a bot speak text during a meeting using text-to-speech Execute send_video_to_meeting Send a video to the meeting through the bot (Google Meet only)

WRITE 2 tools

Write send_chat_message Send a chat message from the bot to the meeting Write send_image_to_meeting Send an image to the meeting through the bot (Google Meet only)

READ 4 tools

Read get_bot_status Get the current status of a meeting bot Read get_chat_messages Get chat messages from the meeting Read get_meeting_transcript Get the transcript from a meeting bot Read get_recording Get the recording URL for a bot

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Attendee MCP Server

Can an AI agent delete data through the Attendee MCP Server MCP server? +

Yes. The Attendee MCP Server server exposes 2 destructive tools including delete_bot_data, remove_meeting_bot. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Attendee MCP Server? +

The Attendee MCP Server server has 2 write tools including send_chat_message, send_image_to_meeting. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Attendee MCP Server.

How many tools does the Attendee MCP Server MCP server expose? +

11 tools across 3 categories: Destructive, Read, Write. 4 are read-only. 7 can modify, create, or delete data.

How do I enforce a policy on Attendee MCP Server? +

Register the Attendee MCP Server MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Attendee MCP Server tool call.

Deterministic rules across all 11 Attendee MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON ATTENDEE →

Free to start. No card required.

11 Attendee MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.