Load one tool category. Categories: uploads, folders, assets, metadata, search, renditions. Call this immediately once user intent is clear.
AI agents call load_category to retrieve information from Adobe Experience Assets Dev MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a classification/lookup tool that retrieves or displays available tool categories to help structure subsequent API requests. It has no side effects, does not execute operations, and does not modify data. This is a Read operation—specifically a navigation/discovery aid for the user interface or tool structure.
From the tool's definition Tool name 'load_category' and description 'Load one tool category' indicate retrieval of category information without modification.
Attacks that exploit this kind of access
Load one tool category. Categories: uploads, folders, assets, metadata, search, renditions. Call this immediately once user intent is clear. It is categorised as a Read tool in the Adobe Experience Assets Dev MCP MCP Server, which means it retrieves data without modifying state.
Register the Adobe Experience Assets Dev MCP server in PolicyLayer and add a rule for load_category: 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 Adobe Experience Assets Dev MCP. Nothing to install.
load_category 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 load_category 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 load_category. 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.
load_category is provided by the Adobe Experience Assets Dev MCP server (stubbedev/adobe-experience-dev-mcp). 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 →