// SCAN REPORT

Dialogbrain

225 tools. 143 can modify or destroy data without limits.

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

Last updated:

143 can modify or destroy data
82 read-only
225 tools total

Community server · catalogue entry checked 22/07/2026 · full schemas captured for 217 of 225 tools

How to control Dialogbrain ↓

TOOL MAP

What Dialogbrain exposes to your agents

Read (82) Write / Execute (125) Destructive / Financial (17)

Running more than one server? Check your whole stack →

CONTEXT-WINDOW COST

What Dialogbrain costs in tokens

51,410 tokens of tool definitions, loaded on every request
26% of a 200k context window
4,150 heaviest tool: agents_update

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

MOST DANGEROUS TOOLS
Critical Risk

The most dangerous Dialogbrain tools

Destructive · Critical agents_delete This tool irreversibly deletes an AI agent and its associated configuration (triggers), which cannot be recovered. Destructive · High agents_trigger_delete The tool permanently removes a trigger (a condition or event that activates AI agent behavior) with no undo capability. Destructive · High ai_filters_delete This tool irreversibly removes data (an AI filter) from the system. Destructive · High ai_tags_delete This tool permanently deletes data (tags) without possibility of recovery, matching the Destructive category definition.

143 of Dialogbrain's 225 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Dialogbrain

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

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
{
  "agents_add_file": {
    "limits": [
      {
        "counter": "agents_add_file_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "agents_activity": {
    "limits": [
      {
        "counter": "agents_activity_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 Dialogbrain — 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 DIALOGBRAIN →

Instant setup, no code required.

FULL CATALOGUE

All 225 Dialogbrain tools

DESTRUCTIVE 17 tools
Destructive agents_delete Permanently delete an AI agent. WARNING: This cannot be undone. The agent and all its triggers will be remove Destructive agents_trigger_delete Delete a trigger from an AI agent. WARNING: This cannot be undone. Destructive ai_filters_delete Permanently delete an AI filter. When to use: - User wants to remove a filter they no longer need This actio Destructive ai_tags_delete Delete a personal AI tag. All thread associations are removed automatically. When to use: - User wants to per Destructive calendar_delete_event Delete an event from Google Calendar. This action cannot be undone. Use with caution. Destructive collections_delete Delete a knowledge collection. If the collection is assigned to agents, prompts, or channels, pass force=true Destructive files_delete Permanently delete files from this workspace by their IDs (generated documents, uploads, screenshots, etc.). Destructive folders_delete 🗑️ Delete an inbox folder. Threads inside become unfiled (not deleted). When to use: - User wants to remove Destructive integrations_remove_endpoints Remove endpoints (tools) from an HTTP-API integration — e.g. junk paths like static assets, /socket.io, or SPA Destructive messages_delete Delete a message from a thread. Supports Telegram, WhatsApp, and other connected channels. Note: Some channels Destructive notes_delete Delete a note by ID from the target notebook. Same identity rules as notes.save — agents can only delete from Destructive reminder_cancel Cancel an active reminder by its trigger ID. Destructive tasks_delete Delete a task from your to-do list by its ID. Destructive threads_delete 🗑️ PERMANENTLY delete conversation thread(s) and their messages + user-facing state (tags, assignments, draft Destructive widgets_delete Delete a livechat widget permanently. This will remove the widget and its embed code will stop working. Exist Destructive youtube_delete_comment Permanently delete a YouTube comment by id (or 'youtube:comment:<id>'). Cannot be undone. Costs 50 quota units Destructive youtube_delete_video Permanently delete a YouTube video by id (or 'youtube:video:<id>'). Cannot be undone. Costs 50 quota units. Ca
EXECUTE 38 tools
Execute agent_handoff Delegate a multi-step task (research, composing messages, booking, scheduling) to the full agentic planner. Us Execute agents_simulate_inbound Replay an inbound message on a thread through the real trigger pipeline and return what would have happened. T Execute android_launch_app Launch an app on the Android device by package name. Example: 'com.whatsapp'. Returns success status and proce Execute android_shell Run an allowlisted shell command on the Android device. First element of cmd array must be allowlisted: input, Execute android_ui_dump Get UI structure dump from the Android device. Uses dumpsys (uiautomator OOM-kills on this build). Returns win Execute background_run Run ANOTHER tool off the critical path: returns INSTANTLY while the target tool runs in the background, so a s Execute browser_attach_meet Attach to THIS meet's bot browser and return a page_id for its live Google Meet tab. Then use the normal brows Execute browser_click Click an element. ref is either an aria-ref token from browser.snapshot ('e7') OR a CSS selector ('button.subm Execute browser_close Close a page opened by browser.open. Execute browser_drag Drag one element onto another. source_ref is the element to grab; target_ref is where to drop. Both are CSS se Execute browser_evaluate Run JavaScript in the page context and return the result. Use for state not in the a11y tree, captcha iframe i Execute browser_fill Fill an input or textarea with the given value. ref is either an aria-ref token from browser.snapshot ('e7') O Execute browser_fill_form Fill multiple form fields in one call. fields is a list of {ref, value} dicts. ref is a CSS selector; value is Execute browser_handle_dialog Respond to a pending JS dialog (alert/confirm/prompt). Pass accept=true for OK or false for Cancel. For prompt Execute browser_hover Hover the mouse over an element (reveals tooltips + hover menus). ref is a CSS selector. Execute browser_navigate_back Navigate back in the page's history (browser back button). Returns the new URL + title. Execute browser_open Open a URL in a remote browser. Saved login cookies are auto-attached when the URL domain matches a claimed br Execute browser_press_key Press a keyboard key (e.g., 'Enter', 'Tab', 'Escape', 'ArrowDown') or a single character. Optional ref focuses Execute browser_resize Resize the page viewport. Useful when a site serves different HTML based on viewport width (mobile vs desktop) Execute browser_select_option Pick option(s) in a native <select> dropdown. Pass value (matches the option's value attr) OR label (matches i Execute browser_tabs Manage tabs within the same BrowserContext as page_id. action ∈ {list, switch, close, new}. For list, returns Execute browser_take_screenshot Capture a PNG screenshot of the page or a specific element. Returns base64-encoded image bytes AND a file_id ( Execute browser_type Type text into an element with per-keystroke delay (organic). Each character dispatches keydown/keypress/keyup Execute browser_wait_for Wait for a selector to appear OR a navigation URL to match a glob pattern. Provide ref (selector) OR url_patte Execute calls_agent_duel Start an agent-vs-agent VOICE test call: two AI voice agents share one LiveKit room — a 'caller' persona agent Execute calls_hangup Hang up an active voice call by call_id. Use after calls.make when the agent decides to terminate before the c Execute calls_meet_browser Attach to a Google Meet bot's live browser to diagnose and recover a bot that isn't visibly joining. Pass the Execute calls_send_to_telegram_call Dispatch a workspace AI agent into a live Telegram GROUP voice chat OR an encrypted call-link conference. FOUR Execute calls_wait Block until a voice call ends (status changes from 'active') or timeout elapses. Returns ended=true with final Execute images_generate Generates a PNG image from a text prompt using Gemini 2.5 Flash Image. Returns a file_id consumable by message Execute integrations_capture_session Restore an expired integration session by capturing the LIVE auth of an open browser page — works for COOKIE s Execute job_escalate Escalate the job to a human. Use when you cannot resolve an issue, someone is not responding, or a situation r Execute linkedin_raw_request Send an arbitrary LinkedIn API request via Unipile's magic route. Only GET and POST methods are allowed. WARNI Execute present_tab Share the agent's browser tab on the live call so everyone sees it as a real screen-share. Pass the page_id yo Execute system_sleep Pause execution for a given number of seconds (max 30). Use when you need to wait for an external process to c Execute videos_generate Generate a short video (5-10s) from a text prompt using BytePlus Seedance. Optionally accepts up to 12 image f Execute workbench_run_python Run Python in an isolated sandbox to process LARGE or paginated tool results without pulling every row into th Execute workspace_switch Re-point the active MCP API key to a different workspace. Pass exactly one of workspace_id or slug (find them
WRITE 87 tools
Write agents_add_file Attach a file to this agent's private knowledge (agent-specific files, not shared with other agents). Workflo Write agents_approve_draft Approve a pending agent draft and send the message. The draft will be sent to the conversation it was generat Write agents_create Create a new AI agent in the workspace. Execution modes: - ai_assisted (default, recommended): Two-phase AI — Write agents_prompt_restore Restore a past version of an agent's prompt_text by version_number. Creates a new version pointing at the rest Write agents_reject_draft Reject a pending agent draft without sending. The draft will be marked as rejected and won't be sent. Use thi Write agents_remove_file Remove a file from this agent's private knowledge. The file itself is not deleted — it's just detached from t Write agents_set_integration Enable or disable a connected workspace integration on an AI agent — this controls which ext<id>_<name> integr Write agents_task_complete Report that a Claude Code agent task has been completed. Call this when you finish processing an agent_task fr Write agents_trigger_create Create a new trigger for an AI agent. Triggers determine when the agent activates. Trigger types: - incoming Write agents_trigger_update Update an existing AI agent trigger. All parameters are optional — only provided fields will be updated. Write agents_update Update an existing AI agent's configuration. All parameters are optional — only provided fields will be updat Write agents_update_from_template Update a forked agent's instructions (prompt) to the latest version of the system template it was created from Write ai_filters_create Create a new AI filter for semantic intent-based message matching. AI filters use vector embeddings (via Voya Write ai_filters_update Update an existing AI filter's name, description, threshold, or active state. When to use: - User wants to re Write ai_tags_add_to_thread Apply one or more AI tags to a thread (manually). When to use: - User wants to label a conversation with one Write ai_tags_create Create a new AI tag (automatic message filter). AI tags are lightweight classifiers that run on every incomin Write ai_tags_remove_from_thread Remove a specific AI tag from a thread. When to use: - User wants to un-label or remove a specific tag from a Write ai_tags_update Update an existing personal AI tag's name, description, icon, color, or active state. When to use: - User wan Write android_close_app Close an app on the Android device (safe method: HOME key + am kill). Never uses am force-stop (corrupts Packa Write android_install_apk Install an app on the Android device from an APK or split bundle (XAPK/APKS — how most large modern apps ship) Write android_key Send a key event to the Android device. Use keycode (e.g., '3' for HOME, '4' for BACK) or common name (e.g., ' Write android_swipe Swipe/drag on the Android device screen from one coordinate to another. Use for scrolling, opening app drawer, Write android_tap Tap on the Android device screen at specified coordinates. Coordinates are in device pixels. Write android_type Type text on the Android device keyboard. Write artifacts_create Host a self-contained HTML page at a stable, default-private, shareable URL — the Artifact experience, in-app. Write artifacts_export_pdf Snapshot an artifact's current version to a PDF saved in the workspace. NOTE: the PDF is a STATIC capture rend Write artifacts_refresh Re-render a data-driven artifact from a small data payload and publish a new version at the SAME URL. The arti Write artifacts_set_access Change an artifact's access level. 'shared' makes the unguessable link the capability (anyone-with-link); 'pri Write artifacts_update Republish an existing artifact with new HTML. The slug and URL stay the SAME; a new version is stored (older v Write browser_attach_identity Switch the page's identity by loading saved cookies + storage. Use only when switching identity mid-page; for Write browser_file_upload Attach files to an <input type=file>. Pass either local_paths (absolute host paths) or data (list of {name, mi Write calendar_create_event Create a new event in Google Calendar. Specify the title, start time, end time, and optionally invite attendee Write calendar_update_event Update an existing event in Google Calendar. Can modify title, time, location, description, and attendees. Onl Write calls_dispatch_translator Send a live speech translator to a call. target decides where: a meet.google.com link → Google Meet bot; a Tel Write calls_make Place an outbound AUDIO/VOICE phone call via Twilio (PSTN) or Telegram (MTProto 1:1 call). Use this any time t Write calls_mute_translation_tts Mute or unmute an active call's live-translation TTS. scope='call' (default, Google Meet sessions ONLY): the t Write calls_send_to_meet Dispatch a workspace AI agent into an active Google Meet call. The agent joins as a participant — it can hear Write calls_set_translation_language Change the target language of an active voice/Meet call's live translator on the fly — no hangup or re-dispatc Write calls_set_translation_languages Set the EXTRA target languages an active voice/Meet call's translator produces for the APP ONLY (subtitles + l Write channels_connect_telegram_bot 🤖 Connect a Telegram Bot (Bot API) channel from its bot token. When to use: - After a bot was created via @B Write collections_add_file Add a file to a knowledge collection. The file must be uploaded and indexed first (files_upload + files_inges Write collections_assign_agent Assign a knowledge collection to an AI agent. Once assigned, the agent's knowledge.query will automatically s Write collections_create Create a named knowledge collection. Collections group files for RAG search. After creating, add files with c Write collections_remove_file Remove a file from a knowledge collection. The file itself is not deleted — only the collection membership is Write collections_unassign_agent Remove a knowledge collection from an AI agent. The collection and its files are not deleted — only the agent Write contacts_add_channel 🔗 Link a new channel identity (email, phone, LinkedIn, etc.) to an existing contact. When to use: - User lea Write contacts_capture_lead 📝 Save the current contact's details as a structured lead (contact + Contacts tab). When to use: - In a webs Write contacts_sync Add a discovered contact and open a conversation thread. Returns thread_id for the new conversation, plus enti Write contacts_update ✏️ Update a contact's profile: name, notes, role, capabilities, birthday, preferred channel. When to use: - U Write documents_create Render a document (PDF / HTML / PPTX / DOCX) and save it to the workspace. This tool has two input pipelines Write feedback_save Save a behavioral rule, preference, or correction that should guide future agent behavior. Use this when the u Write files_ingest Save and index a file into the knowledge base. Use this when the user asks to save, store, or remember a docum Write files_upload Upload a file to DialogBrain and get a file_id for use in messages_send. When to use: - User wants to send a Write folders_create 📁 Create a new inbox folder to organize threads. When to use: - User wants to create a folder to group relat Write group_add Add a specific group to your discovery list by @username or invite link (t.me/...). Groups and channels only Write group_add_member Add a member to an existing group on Telegram or WhatsApp. What this does: - Adds the specified member to the Write group_create Create a new group on a channel (Telegram or WhatsApp). Returns the new group's chat ID and invite link. What Write group_join Join a group and start syncing its messages to your inbox. The group must be in your discovery list (use group Write group_promote_admin Promote a member to admin in an existing group on Telegram or WhatsApp. What this does: - Gives the specified Write instagram_publish_media Publish a photo (IMAGE) or video (REELS) from workspace files to a connected Instagram Business/Creator accoun Write instagram_update_media Update the caption of a published Instagram photo or Reel. Only caption is editable after publish (Instagram l Write integrations_add_endpoints Add one or more API endpoints to an HTTP-API integration as callable tools, merged additively into the integra Write integrations_set_auth Set or update the authentication on an HTTP-API integration, generically. Identify it by integration_id or bas Write job_complete Mark the job as completed. This sanitizes PII from the context and records a completion summary. Use when all Write job_update_context Update the job context by merging new data. Existing keys are preserved unless explicitly overwritten. Use thi Write linkedin_add_comment Add a comment to a LinkedIn post. Use post_id from search results or thread data. Write linkedin_invite Send a connection invitation to a LinkedIn user. Optionally include a personalized message (max 300 characters Write linkedin_update_profile Update the authenticated user's own LinkedIn profile. Supports adding/editing experience entries (role, compan Write messages_edit Edit the text of a message you already sent, in place. Supported on Telegram, WhatsApp, LiveChat, Max.ru, LINE Write messages_forward Forward a message from one thread to another. Supports native Telegram forwarding (preserves original sender a Write messages_send Send a message to a thread, channel, or contact. Supports Telegram, Email, LinkedIn, and other connected chann Write messages_send_email Compose and send an email — with subject, CC/BCC, and attachments. Use for email; for chat messages (Telegram/ Write notes_save Save a fact or note into the agent's memory. Use scope to choose visibility: 'workspace' = visible to every ag Write prompts_prompt_restore Restore a past version of a prompt template by version_number. Creates a new version pointing at the restored Write prompts_update Update a prompt template's name, system instructions, or auto-reply rules. Changes affect every agent using t Write reminder_set Schedule a reminder. One-time reminders fire at a specific datetime. Recurring reminders fire on a schedule (d Write tasks_create Create a new task in your to-do list. Write tasks_update Update an existing task. Set status='done' to complete it, 'cancelled' to cancel. Use summary for completion n Write threads_update ✏️ Update a conversation thread: rename it, add notes/description, or move to a folder. When to use: - User w Write webhooks_configure_enrichment Enable enrichment on an agent's webhook trigger so reference-only webhook payloads are resolved to full data b Write widgets_create Create a new livechat widget for your website. The widget will be created with default settings. You can cust Write widgets_update Update an existing livechat widget configuration. You can change name, theme, auto-reply mode, and other sett Write x_publish_post Publish a post to the connected X (Twitter) account with optional media. Text can include mentions, hashtags, Write youtube_moderate_comment Apply a moderation status to a YouTube comment. Allowed status values: heldForReview, published, rejected, spa Write youtube_post_comment_reply Post a comment on a YouTube video, or reply to an existing comment. Pass video_id for a top-level comment, OR Write youtube_update_video Update title, description, privacy, or tags on a YouTube video. Costs 1600 quota units. Only fields provided a Write youtube_upload_video Upload a workspace-owned video file (file_id) to the connected YouTube channel. Returns video_id + thread_id.
READ 82 tools
Read agents_activity See what you — or another agent in your workspace — actually did over a time window: messages sent, documents Read agents_ask Send a message to an AI agent and get its response. The agent runs with its configured prompt, tools, and kno Read agents_get Get detailed information about a specific AI agent. Returns full agent config including: - Execution configur Read agents_list List all AI agents configured in the workspace. Returns agents with their basic info, trigger count, and know Read agents_list_drafts List pending agent drafts awaiting approval. Shows drafts that have been generated by AI agents but not yet s Read agents_list_files List files directly attached to this agent (agent-specific files, not shared collections). Returns file_id, t Read agents_list_integrations List the workspace integrations enabled (or available) for an AI agent, with each one's workspace_integration_ Read agents_prompt_history List past versions of an agent's prompt_text. Every edit to the agent's prompt is snapshotted to an append-onl Read agents_trace_get Fetch the full execution detail for a single trace — tool executions, events timeline, LLM call spans (with er Read agents_traces_list List recent execution traces for an agent — the same data as /admin/requests, scoped to one agent and readable Read agents_traces_stats Aggregated trace statistics for one agent over the last N days — total runs, success rate, avg duration, error Read ai_filters_list List all AI filters for the current workspace. AI filters are semantic intent-based message filters that use Read ai_filters_test Test a message against an AI filter to check whether it would match. This tool embeds the provided message us Read ai_tags_list List all personal AI tags. AI tags are automatic message filters: the system runs a lightweight classifier on Read analytics_query Answer analytics questions about this workspace's own data (conversations, messages, voice calls) — e.g. 'how Read android_current_app Get the currently focused app and activity on the Android device. Read android_list_apps List installed apps on the Android device. By default returns third-party apps; use all=true for all apps. Read android_screenshot Capture a screenshot from the Android device. Returns JPEG image data encoded as base64. Read artifacts_get Fetch an artifact's metadata by id or slug — title, access level, version, view count, URL. Set include_html=t Read artifacts_list List the workspace's artifacts (most-recently-updated first): title, url, access level, version, view count. S Read browser_console_messages Return console.log/warn/error events captured since the last drain. Filter by level ('log'|'info'|'warning'|'e Read browser_network_requests List HTTP requests the page made since open or last drain. Optional filters: method (GET/POST/...), url_patter Read browser_snapshot Return a YAML aria_snapshot of the page DOM. Each interactive node is tagged with [ref=eN] (e.g. [ref=e7]). Pa Read calendar_check_availability Check when you have free time in Google Calendar. Shows busy periods and free slots in a given time range. Use Read calendar_list_events List events from Google Calendar. Shows upcoming events by default. Can filter by date range and search query. Read calls_get_transcript Get the structured transcript and final state of a voice call by call_id. Returns per-turn rows in chronologic Read calls_list_active List active voice calls in this workspace. Use before calls.make on a Telegram account (only one MTProto call Read calls_list_history Search historical voice calls in this workspace by participant name, contact_id, thread, channel, source, and/ Read collections_list List all knowledge collections in the workspace. Collections are named groups of files used for RAG search. A Read collections_list_files List all files in a knowledge collection with their indexing status and chunk counts. Each returned file has a Read contacts_discover Search for a contact on a live channel (Telegram, WhatsApp, etc.) before adding them. Use this to look up a pe Read contacts_find 👤 Search for contacts in your address book by name or username. When to use: - User asks 'find contact X' or Read contacts_profile 👤 Get full profile for a contact: all channel identities, notes, role, capabilities, birthday. When to use: Read contacts_research Research a person before outreach: returns a synthesized profile (current role, company, location, career hist Read files_get_base64 Download one or more files server-side and return their content as base64-encoded strings. Use this to inspect Read files_info Get metadata and download URLs for files by their IDs. When to use: - After messages_read_history returns att Read files_read Read text content of an attached file. Works for: .txt, .md, .json, code files, and PDFs (after files.ingest e Read group_get_invite_link Export an invite link for an existing group (Telegram). What this does: - Mints a fresh invite link (e.g. t.m Read group_list List groups in this workspace's DISCOVERY/SCORING list (the discovered_group table). ⚠️ This is NOT your mess Read group_preview_messages Read recent public messages from a group without joining it. Only works for groups where can_preview_history=t Read group_scan Scan a group to evaluate its quality before joining. Fetches recent messages, analyzes activity, spam, and eng Read group_search Search for public groups or channels by topic on Telegram (or other channels). Returns matching groups with ti Read images_search Searches images in this workspace by visual content using vector embeddings (Voyage multimodal-3). Pass a text Read instagram_list_media List photos and Reels on the connected Instagram Business/Creator account. Returns id, caption, media_type, pe Read integrations_get_endpoints List every endpoint (operationId, method, path) registered on an HTTP-API integration. Identify it by integrat Read integrations_list List the workspace's external integrations (HTTP-API + MCP), each with its id, provider name, base_url, transp Read job_read_context Read the current job context. Returns the full state of your active job including assignments, escalations, an Read kg_find_entity Find an entity by name in the Knowledge Graph. USE WHEN user mentions a person, project, company by name and Read kg_get_relationships Get relationships for a specific entity from Knowledge Graph. USE WHEN: - 'Кто работает над X?' - filter by w Read knowledge_query Answer questions using knowledge base (uploaded documents, handbooks, files). Use for QUESTIONS that need an Read linkedin_get_company Get a LinkedIn company profile by company ID or vanity name. Returns company name, description, industry, size Read linkedin_get_profile Get a LinkedIn user profile by ID, public identifier (vanity name), or profile URL. Returns name, headline, lo Read linkedin_list_connections List your LinkedIn connections, sorted by most recently added. Read linkedin_list_invitations_sent List your pending sent connection invitations on LinkedIn. Read linkedin_list_reactions List all reactions (likes, celebrates, etc.) on a specific LinkedIn post. Read linkedin_search Search LinkedIn for people, companies, jobs, or posts. Supports filtering by keywords, location, industry, net Read linkedin_search_filters Get LinkedIn search filter parameter IDs. LinkedIn uses internal IDs instead of text for search filters (locat Read messages_read_history Read messages from a conversation thread. Use text_contains to find specific messages by content. Returns the Read notes_recall Recall notes from your notebook. By default returns only your own notes (all scopes, newest first). Pass filte Read notes_search Full-text search in your notebook. By default searches only your own notes. Pass filter_agent_id=<int> to sear Read prompts_get Get full content of a prompt template: system instructions (prompt_text) and auto-reply rules. Run prompts.li Read prompts_list List all prompt templates in this workspace. Returns id + name + description + category so you know which pro Read prompts_prompt_history List past versions of a prompt template's prompt_text. Every edit is snapshotted to an append-only table — use Read reminder_list List your active reminders (both one-time and recurring). Read search_files Search files and attachments across the workspace — by content, filename, document type, or origin. For messag Read search_links Search links/URLs shared across the workspace — by type, owner, or associated contact. For files use search.fi Read search_messages Search message content across all chats — semantic + keyword. Use to find what was said: quotes, topics, info Read search_threads Find or list chat threads/conversations — by topic, participant, unread/unanswered status, or recency. Omit qu Read tasks_list List your tasks, or another agent's tasks (read-only) using from_agent_id. Use filters to narrow results. Read vision_query Look at the screen currently being shared in a meeting and answer a question about it. Returns a natural-langu Read web__local_search Multi-source web research with citations. Returns a synthesized answer with numbered [^1] markers and a citati Read web_fetch Fetches a single URL and returns its content. Use this when you have a specific URL in mind — for example, aft Read web_research Answer a research question from live web sources in one call — returns a synthesized answer with numbered [N] Read web_search Search the web for current information, news, facts, prices, or events. Use this when the user asks about some Read widgets_get Get full configuration of a single livechat widget. Returns all settings including theme, identification, act Read widgets_get_embed_code Get the embed code snippet for a livechat widget. Returns HTML/JavaScript code to add to your website. The co Read widgets_list List all livechat widgets. Returns widgets with their configuration, embed code, and status. Use this when u Read workspace_current Return the workspace this MCP API key is currently routed to, with the caller's role inside it. Use this to co Read workspace_list List every workspace the caller is a member of, with is_current marking the workspace this MCP key is currentl Read youtube_list_comments List comment threads on a YouTube video. Pass video_id (e.g. 'dQw4w9WgXcQ') or channel_ref ('youtube:video:<id Read youtube_list_videos List videos on the connected YouTube channel. Returns id, title, published_at, view_count. Paginate via page_t Read youtube_video_query Ask Gemini about a YouTube video. Pass a video URL and any prompt — verbatim transcript with timestamps, summa
OTHER 1 tools
Other agent_silence End this turn without sending any message. Use when the thread is owned by a human operator after job.escalate
EXPLORE

Related servers

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

UnClick 1658 tools
adminautomation
Nodebench 824 tools
adminautomation
Yaver 811 tools
adminautomation
Binance MCP Server 734 tools
adminautomation
Crow 587 tools
adminautomation
Fortimanager 584 tools
adminautomation
TinyFn 572 tools
adminautomation
Mcp 571 tools
adminautomation
FAQ

Questions about Dialogbrain

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

Yes. The Dialogbrain server exposes 17 destructive tools including agents_delete, agents_trigger_delete, ai_filters_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 87 write tools including agents_add_file, agents_approve_draft, agents_create. 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? +

225 tools across 4 categories: Destructive, Execute, Read, Write. 82 are read-only. 143 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.

Enforce policy on every Dialogbrain tool call.

Deterministic rules across all 225 Dialogbrain tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON DIALOGBRAIN →

Instant setup, no code required.

225 Dialogbrain tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from Dialogbrain's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.