Automagik Tools

122 tools. 64 can modify or destroy data without limits.

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

Last updated:

64 can modify or destroy data
58 read-only
122 tools total

Community server · catalogue entry verified 11/06/2026

How to control Automagik Tools ↓

What Automagik Tools exposes to your agents

Read (58) Write / Execute (38) Destructive / Financial (13)
Critical Risk

The most dangerous Automagik Tools tools

64 of Automagik Tools's 122 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

How to control Automagik Tools

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

Deny destructive operations
{
  "delete_agent_conversation": {
    "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
{
  "react_with": {
    "limits": [
      {
        "counter": "react_with_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "check_is_whatsapp": {
    "limits": [
      {
        "counter": "check_is_whatsapp_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

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

  1. Create a free account and register Automagik Tools — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON AUTOMAGIK TOOLS →

Free to start. No card required.

All 122 Automagik Tools tools

WRITE 29 tools
Write react_with React to message with emoji (auto-detects sender). Args: emoji, to_message_id, phone, instance_name. Returns: Write store_credential Store encrypted credentials for a specific tool. Write add_contact Add contact to local database. Args: phone_number, name, nickname, notes. Returns: confirmation. Write add_source add_source Write add_tool Add a tool to your personal collection. Write convert_json_to_docs convert_json_to_docs Write create_instance create_instance Write create_schedule create_schedule Write disable_schedule Disable an active schedule. Write enable_schedule Enable a disabled schedule. Write manage_chats manage_chats Write manage_contacts manage_contacts Write manage_profiles manage_profiles Write rename_agent_conversation Give a custom name to your conversation session with an agent for easier identification. Write rename_team_collaboration Give a custom name to your team collaboration session for easier identification. Write rename_workflow_execution Give a custom name to your workflow execution session for easier identification. Write send_contact send_contact Write send_location send_location Write send_media send_media Write send_message send_message Write send_poll send_poll Write send_reaction send_reaction Write send_text_message send_text_message Write update_contact Update existing contact in local database. Args: phone_number, name, nickname, notes. Returns: confirmation. Write update_message update_message Write update_schedule update_schedule Write update_source Update a workflow source configuration. Write update_tool_config Update configuration for a tool in your collection. Write upload_template Upload a DOCX file as a template to Google Drive.
READ 58 tools
Read check_is_whatsapp check_is_whatsapp Read check_new_messages Check recent incoming messages. Args: instance_name, hours (lookback), limit. Returns: messages grouped by sen Read check_playground_status Check the current status of the playground environment. Optionally specify an app ID to check a specific appli Read connection_status Check WhatsApp instance connection status. Args: instance_name. Returns: detailed status. Read download_document Download a Google Docs document in specified format. Read download_media Download media from WhatsApp message (image/video/audio/document). Args: message_id, instance_name, filename ( Read extract_placeholders Extract placeholder {{keys}} from a Google Docs template. Read find_chats Find all chat conversations in WhatsApp. Args: instance_name. Returns: list of chats with details. Read find_message Get message details by trace ID. Args: trace_id, instance_name, include_payload. Returns: message details with Read find_person Find person by name with fuzzy search (handles typos, accents, case). Searches local DB + WhatsApp. Args: sear Read genie_memory_stats genie_memory_stats Read get_available_tools List all tools available in the repository that you can add to your collection. Read get_credential Retrieve credentials for a specific tool. Read get_gemini_requests Get the files and searches that Gemini has requested in a session. Read get_group_members Get members of a WhatsApp group with real phone numbers. Args: group_jid (from list_all_groups), instance_name Read get_health Get health status of Spark API and its services. Read get_instance_info Get information about an Evolution API instance Read get_missing_config Identify missing required configuration keys for a tool. Read get_remote_workflow Get detailed information about a specific remote workflow. Read get_schedule Get detailed information about a specific schedule. Read get_source Get detailed information about a specific workflow source. Read get_specific_agent_conversation Get details of a specific conversation session with an agent. Read get_task Get detailed information about a specific task execution. Read get_team_collaboration_details Get detailed results and communication logs from a specific team collaboration session. Read get_team_details Get detailed information about a specific team including its members and capabilities. Read get_tool_config Get current configuration for a tool in your collection. Read get_tool_metadata Get detailed metadata and configuration schema for a specific tool. Read get_workflow Get detailed information about a specific workflow. Read get_workflow_details Get detailed information about a specific workflow including its steps and capabilities. Read get_workflow_execution_details Get detailed results and logs from a specific workflow execution. Read hub_info Get detailed information about the hub and available tools Read list_all_channels list_all_channels Read list_all_groups List all WhatsApp groups you're a member of. Args: instance_name. Returns: groups with member counts. Read list_available_agents List all available agents in the playground that you can interact with. Read list_available_teams List all available agent teams in the playground that you can collaborate with. Read list_available_workflows List all available workflows in the playground that you can execute. Read list_credentials List all stored credentials (metadata only, no secrets). Read list_mounted_tools List all tools mounted in this hub Read list_my_tools List all tools currently in your personal collection. Read list_remote_workflows list_remote_workflows Read list_schedules List all active schedules. Read list_sessions List all active Gemini consultation sessions. Read list_sources List all configured workflow sources. Read list_tasks list_tasks Read list_templates List available Google Docs templates. Read list_workflows list_workflows Read my_connections List WhatsApp instances. Returns: all instances with status. Read my_contacts Get contacts from WhatsApp. Args: instance_name, search query, limit. Returns: list of contacts with names and Read my_conversations Get active WhatsApp conversations. Args: instance_name, conversation_type filter, limit. Returns: list of acti Read my_whatsapp_info Get WhatsApp identity and connection status. Args: instance_name. Returns: number, status, profile info. Read read_messages Read messages from person or conversation. Args: from_phone (number or group ID), instance_name, limit, before Read search Universal search across people, groups, messages, and group members. Args: query (name/phone/keyword), instanc Read validate_json_data Validate JSON data and optionally check against template placeholders. Read view_agent_conversation_history View all your conversation sessions with a specific agent. Read view_agent_memories View what an agent remembers about your interactions and conversations. Read view_team_collaboration_history View all your collaboration sessions with a specific team. Read view_team_memories View what a team remembers about your collaborations and shared experiences. Read view_workflow_execution_history View all your execution sessions with a specific workflow.

Related servers

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

Questions about Automagik Tools

Can an AI agent delete data through the Automagik Tools MCP server? +

Yes. The Automagik Tools server exposes 13 destructive tools including delete_agent_conversation, delete_credential, delete_message. 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 Automagik Tools? +

The Automagik Tools server has 29 write tools including react_with, store_credential, add_contact. 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 Automagik Tools.

How many tools does the Automagik Tools MCP server expose? +

122 tools across 4 categories: Destructive, Execute, Read, Write. 58 are read-only. 64 can modify, create, or delete data.

How do I enforce a policy on Automagik Tools? +

Register the Automagik Tools 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 Automagik Tools tool call.

Deterministic rules across all 122 Automagik Tools tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

122 Automagik Tools tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.