owners_add
Register a business owner. Owners are the contacts allowed to give the Assistant configuration instructions; they are stored on the Assistant's restriction trigger (sender_filter). Resolves a telegram/maxru @username to the numeric peer id so the owner is actually matched on inbound messages. Fai...
This record as markdown: /tools/io-github-saloprj-dialogbrain/owners-add.md
What owners_add does on Dialogbrain
AI agents use owners_add 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 |
|---|---|---|---|
channel | string | — | Channel the contact belongs to. OMIT to use the default ('telegram'). |
contact | string | Yes | Owner contact: a @username or numeric user id (telegram), or a phone number (whatsapp/maxru). E.g. '@username' or a numeric id. |
send_welcome | boolean | — | Send a welcome message to the new owner. OMIT to use the default (true). |
Parameters from the server's own tool schema.
Why owners_add is rated Medium
This is a Write operation because it creates and persistently modifies authorization configuration data (storing owner contacts in a restriction filter). While it doesn't execute arbitrary code or delete data, it does irreversibly alter access controls for a unified messaging system.
From the tool's definition Tool description explicitly states it will 'Register a business owner' and 'are stored on the Assistant's restriction trigger'; this creates/modifies authorization data by adding contacts to an access control list.
Attacks that exploit this kind of access
The rule that runs owners_add 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 owners_add, this is the rule to start with:
owners_add 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Dialogbrain, apply this rule, and every owners_add call is checked against it from then on.
Questions about owners_add
Register a business owner. Owners are the contacts allowed to give the Assistant configuration instructions; they are stored on the Assistant's restriction trigger (sender_filter). Resolves a telegram/maxru @username to the numeric peer id so the owner is actually matched on inbound messages. Fails with: - already_exists: this contact is already an owner - self_owner: the contact is the connected account itself (forbidden) - contact_not_found: the @username does not exist on that channel On success, ATTEMPTS a welcome message and returns welcome_status ('sent' | 'failed' | 'skipped') — 'failed' is normal for a contact with no existing dialog / restricted DMs / nonexistent handle (the owner is still registered and recognized once they message first). Report the real welcome_status; never claim a welcome was delivered unless welcome_status == 'sent'. 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.
owners_add accepts 3 parameters: channel, contact, send_welcome. Required: contact. The full parameter table on this page comes from the server's own tool schema.
Register the Dialogbrain MCP server in PolicyLayer and add a rule for owners_add: 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.
owners_add is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the owners_add 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.
Set action: deny in the PolicyLayer policy for owners_add. 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.
owners_add 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.
More on Dialogbrain, and thousands of servers like it.
This server
Across the catalogue