// SCAN REPORT

Dialogbrain

157 tools. 95 can modify or destroy data without limits.

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

Last updated: 6 Jun 2026

95 can modify or destroy data

62 read-only

157 tools total

Free to start. No card required.

TOOL MAP

Read (62) Write / Execute (77) Destructive / Financial (18)

CONTEXT-WINDOW COST

38,562 tokens of tool definitions, loaded on every request

19% of a 200k context window

3,142 heaviest tool: agents_update

Full per-tool breakdown → Model it in the token calculator →

WHAT CAN GO WRONG

Destructive tools (agents_delete, agents_remove_file, agents_trigger_delete) permanently delete resources. There is no undo. An agent calling these in a retry loop causes irreversible damage.

Write operations (agent_handoff, agent_silence, agents_add_file) modify state. Without rate limits, an agent can make hundreds of changes in seconds — faster than any human can review or revert.

Execute tools (agents_activity, agents_simulate_inbound, agents_trigger_create) trigger processes with side effects. Builds, notifications, workflows — all fired without throttling.

RECOMMENDED RULES

Deny destructive operations

{
  "agents_delete": {
    "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

{
  "agent_handoff": {
    "limits": [
      {
        "counter": "agent_handoff_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "agents_ask": {
    "limits": [
      {
        "counter": "agents_ask_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

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

ALL 157 DIALOGBRAIN TOOLS

DESTRUCTIVE 18 tools

Destructive agents_delete Destructive agents_remove_file Destructive agents_trigger_delete Destructive ai_filters_delete Destructive ai_tags_delete Destructive ai_tags_remove_from_thread Destructive calendar_delete_event Destructive collections_delete Destructive collections_remove_file Destructive collections_unassign_agent Destructive folders_delete Destructive messages_delete Destructive notes_delete Destructive reminder_cancel Destructive tasks_delete Destructive widgets_delete Destructive youtube_delete_comment Destructive youtube_delete_video

EXECUTE 7 tools

Execute agents_activity Execute agents_simulate_inbound Execute agents_trigger_create Execute agents_trigger_update Execute calls_wait Execute group_join Execute system_sleep

WRITE 70 tools

Write agent_handoff Write agent_silence Write agents_add_file Write agents_approve_draft Write agents_create Write agents_prompt_history Write agents_prompt_restore Write agents_reject_draft Write agents_task_complete Write agents_update Write agents_update_from_template Write ai_filters_create Write ai_filters_update Write ai_tags_add_to_thread Write ai_tags_create Write ai_tags_update Write calendar_create_event Write calendar_update_event Write calls_hangup Write calls_make Write calls_send_to_meet Write calls_send_to_telegram_call Write channels_connect_telegram_bot Write collections_add_file Write collections_assign_agent Write collections_create Write contacts_add_channel Write contacts_discover Write contacts_sync Write contacts_update Write documents_create Write feedback_save Write files_ingest Write files_upload Write folders_create Write group_add Write group_add_member Write group_create Write group_promote_admin Write images_generate Write instagram_publish_media Write instagram_update_media Write job_complete Write job_escalate Write job_update_context Write linkedin_add_comment Write linkedin_invite Write linkedin_raw_request Write linkedin_update_profile Write messages_forward Write messages_send Write messages_send_email Write notes_save Write present_tab Write prompts_prompt_history Write prompts_prompt_restore Write prompts_update Write reminder_set Write tasks_create Write tasks_update Write threads_update Write videos_generate Write widgets_create Write widgets_update Write workspace_current Write workspace_switch Write youtube_moderate_comment Write youtube_post_comment_reply Write youtube_update_video Write youtube_upload_video

READ 62 tools

Read agents_ask Read agents_get Read agents_list Read agents_list_drafts Read agents_list_files Read agents_trace_get Read agents_traces_list Read agents_traces_stats Read ai_filters_list Read ai_filters_test Read ai_tags_list Read calendar_check_availability Read calendar_list_events Read calls_get_transcript Read calls_list_active Read calls_list_history Read collections_list Read collections_list_files Read contacts_find Read contacts_profile Read files_get_base64 Read files_info Read files_read Read group_list Read group_preview_messages Read group_scan Read group_search Read images_search Read instagram_list_media Read job_read_context Read kg_find_entity Read kg_get_relationships Read knowledge_query Read linkedin_get_company Read linkedin_get_profile Read linkedin_list_connections Read linkedin_list_invitations_sent Read linkedin_list_reactions Read linkedin_search Read linkedin_search_filters Read messages_read_history Read notes_recall Read notes_search Read prompts_get Read prompts_list Read reminder_list Read search_files Read search_links Read search_messages Read search_threads Read tasks_list Read vision_query Read web__local_search Read web_fetch Read web_search Read widgets_get Read widgets_get_embed_code Read widgets_list Read workspace_list Read youtube_list_comments Read youtube_list_videos Read youtube_video_query

FAQ

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

Yes. The Dialogbrain server exposes 18 destructive tools including agents_delete, agents_remove_file, agents_trigger_delete. 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 Dialogbrain? +

The Dialogbrain server has 70 write tools including agent_handoff, agent_silence, agents_add_file. 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 Dialogbrain.

How many tools does the Dialogbrain MCP server expose? +

157 tools across 4 categories: Destructive, Execute, Read, Write. 62 are read-only. 95 can modify, create, or delete data.

How do I enforce a policy on Dialogbrain? +

Register the Dialogbrain 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.

// RELATED SERVERS

Other MCP servers with similar tools.

Starter policies for each. Same risk classification, live on your fleet in minutes.

Enforce policy on every Dialogbrain tool call.

Deterministic rules across all 157 Dialogbrain tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

SECURE DIALOGBRAIN →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

Dialogbrain

// TOOL MAP

// CONTEXT-WINDOW COST

// WHAT CAN GO WRONG

// RECOMMENDED RULES

// ALL 157 DIALOGBRAIN TOOLS

// FAQ