Send a keystroke to Affinity with optional modifiers
AI agents invoke affinity_keystroke 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.
Sending keystrokes with optional modifiers (e.g., Cmd+Z, Cmd+S, Delete) to a creative application via AppleScript/System Events constitutes executing arbitrary UI actions. The effects are highly dependent on arguments — keystrokes could trigger saves, deletions, exports, or destructive edits.
From the tool's definition Send a keystroke to Affinity with optional modifiers
Attacks that exploit this kind of access
Send a keystroke to Affinity with optional modifiers. 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_keystroke: 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_keystroke 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_keystroke 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_keystroke. 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_keystroke 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 →