Select a drawing/editing tool via keyboard shortcut
AI agents invoke affinity_select_tool to trigger actions in Affinity MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool triggers keyboard shortcut execution via AppleScript/System Events to change the active tool in Affinity. It performs an action (sending keystrokes) that affects the application state. While selecting a tool alone doesn't create or destroy data, it executes system-level input simulation that can have downstream effects depending on what operations follow.
From the tool's definition Select a drawing/editing tool via keyboard shortcut
Attacks that exploit this kind of access
Select a drawing/editing tool via keyboard shortcut. It is categorised as a Execute tool in the Affinity MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Affinity MCP Server MCP server in PolicyLayer and add a rule for affinity_select_tool: 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 Affinity MCP Server. Nothing to install.
affinity_select_tool is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the affinity_select_tool 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 affinity_select_tool. 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.
affinity_select_tool is provided by the Affinity MCP Server MCP server (sekharmalla/affinity-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 →