messages_send

SERVERDialogbrain SOURCEhttps://api.dialogbrain.com/mcp

Medium RISK CLASS

Category Write

Parameters 80 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-saloprj-dialogbrain/messages-send.md

WHAT IT DOES

What messages_send does on Dialogbrain

AI agents use messages_send to create or update resources in Dialogbrain, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Dialogbrain environment.

Parameter	Type	Required	Description
`text`	string	—	Message text to send. Optional if attachments provided.
`format`	string	—	Message format
`silent`	boolean	—	Send without notification
`thread_id`	string	—	Target thread. OMIT to reply in the same chat you received the triggering message from — the backend defaults to the current thread. Pass an explicit value ONLY
`attachments`	array	—	Array of integer file IDs to send as attachments (images, documents, any files). Get file IDs from collections.list_files (field `file_id`), search.files (field
`recipient_name`	string	—	Name of person to send to (e.g., 'Jane', 'John'). Tool will auto-resolve channel. Optional if thread_id provided.
`recipient_username`	string	—	Telegram @username to message (e.g. '@some_username'). Use this for a Telegram user NOT yet in contacts — it resolves the handle, adds the contact, and creates
`reply_to_message_id`	string	—	ID of message to reply to (optional)

Parameters from the server's own tool schema.

RISK

Why messages_send is rated Medium

This tool creates new content (messages, comments, attachments) across multiple communication channels, which is a reversible write operation. It does not execute arbitrary code, delete data, or move money. However, severity is high because an AI agent sending unsolicited messages across multiple channels (email, social media, messaging apps) could cause reputational damage, privacy violations, or harassment.

From the tool's definition Tool performs 'Send a message' action that creates new messages across multiple communication channels (Telegram, Email, LinkedIn).

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs messages_send safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Dialogbrain, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For messages_send, this is the rule to start with:

messages_send Rate-limited

messages_send stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "messages_send": {
      "limits": [
        {
          "counter": "messages_send_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Dialogbrain, apply this rule, and every messages_send call is checked against it from then on.

FAQ

Questions about messages_send

What does the messages_send tool do? +

Send a message to a thread, channel, or contact. Supports Telegram, Email, LinkedIn, and other connected channels. For LinkedIn posts (comment_thread kind), this posts a comment on the post. Can automatically resolve recipients and channels when not specified. Can send files/images/documents as attachments — pass attachments=[file_id, ...] with integer file IDs obtained from collections.list_files, search.files, or files.search. text is optional when attachments are provided. It is categorised as a Write tool in the Dialogbrain MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does messages_send accept? +

messages_send accepts 8 parameters: text, format, silent, thread_id, attachments, recipient_name, recipient_username, reply_to_message_id. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on messages_send? +

Register the Dialogbrain MCP server in PolicyLayer and add a rule for messages_send: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Dialogbrain. Nothing to install.

What risk level is messages_send? +

messages_send is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit messages_send? +

Yes. Add a rate_limit block to the messages_send rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block messages_send completely? +

Set action: deny in the PolicyLayer policy for messages_send. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides messages_send? +

messages_send is provided by the Dialogbrain MCP server (https://api.dialogbrain.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Dialogbrain, and thousands of servers like it.

This server

All 222 Dialogbrain tools →

Across the catalogue

sms_send on Twilio SMS MCP Server →send-draft on Meme MCP Server →mail_send_draft on Apple Apps MCP → The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →