get_brand
AI agents call get_brand to retrieve information from Mattcoatsworth Canva without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'get_brand' tool appears to retrieve brand information from Canva, consistent with the 'get_*' pattern of other read-only tools on this server. Even without an explicit description, the naming convention and context strongly suggest a data retrieval operation with no side effects. Confidence is moderately high despite the empty description, as the sibling tools establish a clear pattern.
From the tool's definition Tool name is 'get_brand' which follows the naming pattern of sibling read-only tools (get_asset, get_design, get_user). No destructive or side-effect keywords present. Description is empty, limiting specificity.
Attacks that exploit this kind of access
get_brand. It is categorised as a Read tool in the Mattcoatsworth Canva MCP Server, which means it retrieves data without modifying state.
Register the Mattcoatsworth Canva MCP server in PolicyLayer and add a rule for get_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 Mattcoatsworth Canva. Nothing to install.
get_brand is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_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 get_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.
get_brand is provided by the Mattcoatsworth Canva MCP server (@iflow-mcp/mattcoatsworth-canva-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →