update_brand
Partial-merge update to the org's brand profile (name, tagline, palette, font_pair, social, address, etc). Only the fields you pass are written; everything else is preserved. Read current values first with get_status. Logos and favicon are asset_ids (upload via the dashboard or media API and pass...
This record as markdown: /tools/9d9dev-mcp/update-brand.md
What update_brand does on 9d9dev
AI agents use update_brand to create or update resources in 9d9dev, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your 9d9dev environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
brand | object | Yes | Any subset of brand fields. Unknown fields are rejected. |
org_id | string | — | Optional. Defaults to the org_id in this project's .9d9.json — only pass to override. |
Parameters from the server's own tool schema.
Why update_brand is rated Medium
An AI agent can call update_brand faster than any human can review: one bad instruction and it creates or modifies resources in 9d9dev by the hundred, each call as confident as the last.
Risk signalsHigh parameter count (41 properties) · Bulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
The rule that runs update_brand safely
PolicyLayer is an MCP gateway: it sits between your AI agents and 9d9dev, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For update_brand, this is the rule to start with:
update_brand 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 9d9dev, apply this rule, and every update_brand call is checked against it from then on.
Questions about update_brand
Partial-merge update to the org's brand profile (name, tagline, palette, font_pair, social, address, etc). Only the fields you pass are written; everything else is preserved. Read current values first with get_status. Logos and favicon are asset_ids (upload via the dashboard or media API and pass the returned id). It is categorised as a Write tool in the 9d9dev MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
update_brand accepts 2 parameters: brand, org_id. Required: brand. The full parameter table on this page comes from the server's own tool schema.
Register the 9d9dev MCP server in PolicyLayer and add a rule for update_brand: 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 9d9dev. Nothing to install.
update_brand 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 update_brand 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 update_brand. 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.
update_brand is provided by the 9d9dev MCP server (@9d9dev/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on 9d9dev, and thousands of servers like it.
This server
Across the catalogue