rewrite_text
Rewrite text in a specified tone using Apple Intelligence (on-device Foundation Models). Requires macOS 26+ with Apple Silicon.
This record as markdown: /tools/io-github-heznpc-iconnect/rewrite-text.md
What rewrite_text does on Iconnect
AI agents invoke rewrite_text to trigger actions in Iconnect. 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.
Why rewrite_text is rated High
This tool triggers an on-device AI model execution to rewrite text. While it doesn't delete data or move money, it runs an AI inference operation that produces transformed output, which classifies it as Execute. Severity is medium because a misuse could produce misleading or manipulated content, but blast radius is limited to text transformation.
From the tool's definition 'Rewrite text in a specified tone using Apple Intelligence (on-device Foundation Models)' — invokes an on-device AI model to transform/process text, constituting an external computational operation
Attacks that exploit this kind of access
The rule that runs rewrite_text safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Iconnect, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For rewrite_text, this is the rule to start with:
rewrite_text stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Iconnect, apply this rule, and every rewrite_text call is checked against it from then on.
Questions about rewrite_text
Rewrite text in a specified tone using Apple Intelligence (on-device Foundation Models). Requires macOS 26+ with Apple Silicon. It is categorised as a Execute tool in the Iconnect MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Iconnect MCP server in PolicyLayer and add a rule for rewrite_text: 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 Iconnect. Nothing to install.
rewrite_text 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 rewrite_text 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 rewrite_text. 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.
rewrite_text is provided by the Iconnect MCP server (iconnect-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Iconnect, and thousands of servers like it.
Across the catalogue