# local_llm_generate Generate text using a local Ollama model. Runs entirely on your machine — no data sent to any cloud. Agent View of the PolicyLayer registry record for `local_llm_generate`. HTML page: https://policylayer.com/tools/io-github-heznpc-iconnect/local-llm-generate ## Facts - Tool: `local_llm_generate` - Server: Iconnect (`iconnect-mcp`) — https://policylayer.com/tools/io-github-heznpc-iconnect.md - Install: `npx -y iconnect-mcp` - Homepage: https://github.com/heznpc/iConnect - Risk category: Execute (High risk) - Registry record: grade F, identity unverified - Server rate-limited: no - Parameters: 0 - Recommended policy verdict: Rate-limited ## Example call (MCP tools/call, JSON-RPC 2.0) ```json { "jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": { "name": "local_llm_generate", "arguments": {} } } ``` ## Why local_llm_generate is rated High This tool executes a local model inference process (Ollama) on the user's machine. While it doesn't delete data or move money, it runs an external process whose behavior depends on the prompt/arguments provided. An AI agent could misuse it to generate harmful content or exhaust local compute resources. Severity is medium since effects are local and no data is exfiltrated to the cloud. From the tool's own definition: "'Generate text using a local Ollama model' — triggers execution of a local LLM inference process on the machine" ## Use case AI agents invoke local_llm_generate 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. ## Recommended policy (PolicyLayer) Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Iconnect: ```json { "version": "1", "default": "deny", "tools": { "local_llm_generate": { "limits": [ { "counter": "local_llm_generate_rate", "window": "minute", "max": 10, "scope": "grant" } ] } } } ``` ## Other tools on Iconnect (278) - `delete_contact` — Destructive — https://policylayer.com/tools/io-github-heznpc-iconnect/delete-contact.md - `delete_event` — Destructive — https://policylayer.com/tools/io-github-heznpc-iconnect/delete-event.md - `delete_note` — Destructive — https://policylayer.com/tools/io-github-heznpc-iconnect/delete-note.md - `delete_photos` — Destructive — https://policylayer.com/tools/io-github-heznpc-iconnect/delete-photos.md - `delete_playlist` — Destructive — https://policylayer.com/tools/io-github-heznpc-iconnect/delete-playlist.md - `delete_reminder` — Destructive — https://policylayer.com/tools/io-github-heznpc-iconnect/delete-reminder.md - `delete_reminder_list` — Destructive — https://policylayer.com/tools/io-github-heznpc-iconnect/delete-reminder-list.md - `delete_shortcut` — Destructive — https://policylayer.com/tools/io-github-heznpc-iconnect/delete-shortcut.md - `memory_forget` — Destructive — https://policylayer.com/tools/io-github-heznpc-iconnect/memory-forget.md - `move_note` — Destructive — https://policylayer.com/tools/io-github-heznpc-iconnect/move-note.md - `remove_from_playlist` — Destructive — https://policylayer.com/tools/io-github-heznpc-iconnect/remove-from-playlist.md - `semantic_clear` — Destructive — https://policylayer.com/tools/io-github-heznpc-iconnect/semantic-clear.md - `spotlight_clear` — Destructive — https://policylayer.com/tools/io-github-heznpc-iconnect/spotlight-clear.md - `trash_file` — Destructive — https://policylayer.com/tools/io-github-heznpc-iconnect/trash-file.md - `activate_tab` — Execute — https://policylayer.com/tools/io-github-heznpc-iconnect/activate-tab.md - `ai_agent` — Execute — https://policylayer.com/tools/io-github-heznpc-iconnect/ai-agent.md - `ai_chat` — Execute — https://policylayer.com/tools/io-github-heznpc-iconnect/ai-chat.md - `ai_plan_metrics` — Execute — https://policylayer.com/tools/io-github-heznpc-iconnect/ai-plan-metrics.md - `connect_bluetooth` — Execute — https://policylayer.com/tools/io-github-heznpc-iconnect/connect-bluetooth.md - `disconnect_bluetooth` — Execute — https://policylayer.com/tools/io-github-heznpc-iconnect/disconnect-bluetooth.md - `edit_shortcut` — Execute — https://policylayer.com/tools/io-github-heznpc-iconnect/edit-shortcut.md - `event_subscribe` — Execute — https://policylayer.com/tools/io-github-heznpc-iconnect/event-subscribe.md - `generate_image` — Execute — https://policylayer.com/tools/io-github-heznpc-iconnect/generate-image.md - `generate_text` — Execute — https://policylayer.com/tools/io-github-heznpc-iconnect/generate-text.md - `gws_raw` — Execute — https://policylayer.com/tools/io-github-heznpc-iconnect/gws-raw.md - `import_shortcut` — Execute — https://policylayer.com/tools/io-github-heznpc-iconnect/import-shortcut.md - `keynote_start_slideshow` — Execute — https://policylayer.com/tools/io-github-heznpc-iconnect/keynote-start-slideshow.md - `launch_app` — Execute — https://policylayer.com/tools/io-github-heznpc-iconnect/launch-app.md - `minimize_window` — Execute — https://policylayer.com/tools/io-github-heznpc-iconnect/minimize-window.md - `move_window` — Execute — https://policylayer.com/tools/io-github-heznpc-iconnect/move-window.md - …and 248 more: https://policylayer.com/tools/io-github-heznpc-iconnect.md ## For agents This record is a snapshot. Live verdicts and the full registry: - Check every server in your MCP config at once: `npx -y policylayer stack` - Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md) - Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events` --- Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=io-github-heznpc-iconnect · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/io-github-heznpc-iconnect