AI agents call list_available_filters to retrieve information from Graphics without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a simple enumeration/listing operation with no side effects. It queries the set of available filters but does not apply them, create resources, execute arbitrary code, or modify any state. The blast radius of misuse is minimal—an agent could only consume API resources or spam requests.
From the tool's definition Tool name 'list_available_filters' and description 'List all available image filters' indicate a read-only operation that retrieves and enumerates metadata without modifying any data.
Attacks that exploit this kind of access
List all available image filters. It is categorised as a Read tool in the Graphics MCP Server, which means it retrieves data without modifying state.
Register the Graphics MCP server in PolicyLayer and add a rule for list_available_filters: 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 Graphics. Nothing to install.
list_available_filters 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 list_available_filters 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 list_available_filters. 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.
list_available_filters is provided by the Graphics MCP server (lesleslie/graphics-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 →