High-risk tools in TermPipe MCP

High severity TermPipe MCP MCP Server 44 of 119 tools

44 of the 119 tools in TermPipe MCP are classified as high risk. This page profiles those tools specifically, with recommended policy actions and the attack patterns that target them.

Every operation listed below is an action PolicyLayer recommends controlling at the transport layer. Open any tool to see the full profile, risk score, and YAML policy snippet.

Tools at high risk

boot Execute

Mid-session context refresh with integrated briefing.
build Execute

build
cond_clipboard_paste Execute

Trigger Ctrl+V to paste current clipboard content into active window.
cond_daemon_send Execute

cond_daemon_send
cond_focus Execute

Focus a window by app-id or name (fuzzy match).
cond_key Execute

Send a key combination. Separate keys with space or ,,.
cond_launch Execute

Launch an application by name (uses cond app database, fuzzy match).
cond_mouse_click Execute

Click a mouse button.
cond_mouse_move Execute

Move the mouse cursor.
cond_move_window Execute

Move a window. x/y can be pixels or 0.0-1.0 percentage of screen.
cond_ocr Execute

Capture active window, run AI OCR (qwen-vl via iflow), copy result to clipboard.
cond_ocr_file Execute

Run AI OCR on an existing image file and copy result to clipboard.
cond_register_hotkey_input Execute

Register a hotkey to execute input commands (type, key, click, etc).
cond_register_hotkey_script Execute

Register a hotkey to execute a shell script.
cond_resize_window Execute

Resize a window. w/h can be pixels or 0.0-1.0 percentage.
cond_restore_layout Execute

Restore a previously saved window layout.
cond_snap Execute

Snap active window to a screen region.
cond_subscribe Execute

cond_subscribe
cond_type Execute

Type text into the active window via compositor input injection.
cond_verify_launch Execute

cond_verify_launch
cond_visual_query Execute

cond_visual_query
debug_assist Execute

debug_assist
gemini_debug Execute

gemini_debug
ifp_send Execute

Send a prompt to local omniproxy (qwen2.5-coder-7b-instruct).
interact_with_process Execute

Send input to a running process (REPL, interactive shell, etc).
launch_app Execute

Launch an application via normalized launch script.
reload_tools Execute

Hot-reload all tool modules.
smart_replace Execute

smart_replace
start_search Execute

start_search
stop_search Execute

Stop and clean up a search.
termf_exec Execute

Execute a shell command via TermPipe (existing method, preserved).
termf_hsp_pipeline Execute

termf_hsp_pipeline
termf_live_continue Execute

Execute another command in an existing terminal session.
termf_live_exec Execute

termf_live_exec
termf_nlp Execute

Execute NLP command via TermPipe. Translates natural language to CLI.
termf_nlp_alias Execute

Generate and install a shell alias/function from natural language.
wbind_action Execute

wbind_action
wbind_launch_and_focus Execute

Launch an app and bring it to a known state.
workspace_ask Execute

workspace_ask
workspace_await_approval Execute

workspace_await_approval
workspace_await_task_approval Execute

workspace_await_task_approval
workspace_init Execute

workspace_init
workspace_task_create Execute

workspace_task_create
workspace_task_query Execute

workspace_task_query

Attacks that target this class

High-risk tools in any server share these documented attack patterns. Each links to the full case and the defensive policy.

Destructive Action Autonomy
Runaway Tool Loops
Prompt Injection via Tool Results

High-risk tools in TermPipe MCP

Tools at high risk

Attacks that target this class

More on TermPipe MCP

Enforce policy on every TermPipe MCP tool call.