Displayed all available AI assistant tools
Public
Displayed all available AI assistant tools
Agent
Grok
Model
Grok 4.5
Shared
Jul 16, 4:54 PM
Messages172
Downloads0
Identified built-in tools.
UnderstandChecked MCP tools availability.
UnderstandCompiled and presented full tool inventory.
VerifyHook executed: hook
Show me all the tools you have
The user wants to see all the tools I have available. I should list them comprehensively based on what I know from my system prompt and available tools. Let me organize this clearly.
I'll list the built-in tools and check which MCP tools are available right now.
Hook executed: hook
The search only returned one tool with a high score match. Let me try more specific searches for each MCP server to get a fuller picture.
Let me pull a fuller picture of the MCP tools across servers.
Hook executed: hook
Hook executed: hook
Hook executed: hook
I have a complete picture of built-in tools and MCP tools. Let me present this clearly to the user.
Here’s the full tool inventory available in this session.
| Tool | Purpose |
|---|---|
read_file | Read files (text, PDF, PPTX, images, notebooks) |
write | Create or overwrite files |
search_replace | Edit files with exact string replacement |
list_dir | List directory contents |
grep | Search file contents with ripgrep |
| Tool | Purpose |
|---|---|
run_terminal_command | Run bash commands (foreground or background) |
get_command_or_subagent_output | Poll background task / subagent output |
kill_command_or_subagent | Stop a background task or subagent |
monitor | Stream events from long-running commands |
| Tool | Purpose |
|---|---|
spawn_subagent | Launch specialized agents (general-purpose, explore, plan) |
todo_write | Track multi-step task progress |
enter_plan_mode / exit_plan_mode | Plan before coding, then present for approval |
ask_user_question | Ask you multiple-choice questions |
update_goal | Report progress on an active goal |
| Tool | Purpose |
|---|---|
scheduler_create | Create recurring/one-shot scheduled prompts |
scheduler_delete | Cancel a scheduled task |
scheduler_list | List active scheduled tasks |
| Tool | Purpose |
|---|---|
web_search | Search the web |
web_fetch | Fetch a URL as markdown |
open_page / open_page_with_find | Browse pages (full or pattern-matched) |
x_user_search | Find X users |
x_semantic_search | Semantic search of posts |
x_keyword_search | Advanced X post search |
x_thread_fetch | Fetch a post thread |
| Tool | Purpose |
|---|---|
image_gen | Generate images from text |
image_edit | Edit/transform images |
image_to_video | Animate a single image into video |
reference_to_video | Generate video from multiple reference images |
| Tool | Purpose |
|---|---|
search_tool | Discover MCP tools and their schemas |
use_tool | Call an MCP tool by qualified name |
tasks (connected — 6 tools)| Tool | Purpose |
|---|---|
tasks__create | Create a scheduled task / reminder |
tasks__list | List active scheduled tasks |
tasks__update | Update name, prompt, schedule, notifications |
tasks__pause | Pause or resume a schedule |
tasks__delete | Archive/deactivate a task |
tasks__get_results | Get recent execution results |
traces and vercelStill connecting (or not yet exposing tools). Their tools will show up via search_tool once ready.
Not tools themselves, but instruction packs I can load for specialized work — e.g. pptx, docx, xlsx, review, design, shadcn, Vercel/Next.js skills, check-work, imagine, etc.
Summary: ~35 built-in tools + 6 MCP tools from tasks. Want a deep dive on any category (e.g. media, agents, scheduling)?
Run a test that demonstrates all these tools reversibily
The user wants me to run a test that demonstrates all the tools I have, in a reversible way. This is a comprehensive demonstration of tools without making permanent/destructive changes. I'll run a reversible test that demonstrates all the tools I have access to. I'll use temporary locations and clean everything up afterward so nothing gets left behind.
I'll run a reversible end-to-end demo: use a temp sandbox, exercise each tool category, then clean up everything we create.
Hook executed: hook
Hook executed: hook
>DEMO_DIR=$(mktemp -d /tmp/grok-tool-demo.XXXXXX) && echo "DEMO_DIR=$DEMO_DIR" && mkdir -p "$DEMO_DIR"/{src,out} && printf 'hello world\nline two\n' > "$DEMO_DIR/src/sample.txt" && printf 'export function add(a, b) { return a + b; }\n' > "$DEMO_DIR/src/math.js" && ls -la "$DEMO_DIR" && ls -la "$DEMO_DIR/src"Hook executed: hook
Plan:
Good progress. Sandbox is at /tmp/grok-tool-demo.nhtuB3. Let me continue with filesystem tools, web tools, etc. in parallel where possible.
Hook executed: hook
Hook executed: hook
Hook executed: hook
Hook executed: hook
Hook executed: hook
Filesystem tools work. Now web, X, background, scheduler, MCP, media in parallel batches.
Hook executed: hook
Hook executed: hook
Plan:
>for i in 1 2 3 4 5; do echo "tick $i $(date +%H:%M:%S)"; sleep 1; done; echo DONEHook executed: hook
Hook executed: hook
Task backgrounded: background task
Good. Let me get the background task output, list schedulers, spawn a read-only explore subagent, call MCP tools, generate a simple image, monitor briefly
, etc.
Hook executed: hook
Hook executed: hook
Hook executed: hook
Hook executed: hook
Hook executed: hook
Subagent spawned: unknown
Task completed: background task
Subagent finished: unknown
Good progress. Let me:
Hook executed: hook
Hook executed: hook
>while true; do echo "still running $(date +%H:%M:%S)"; sleep 2; doneHook executed: hook
Hook executed: hook
Hook executed: hook
Task backgrounded: background task
Task backgrounded: background task
Task completed: background task
Good progress. Now I need to:
Cleaning up created tasks and finishing the remaining demos.
Hook executed: hook
Hook executed: hook
Hook executed: hook
Hook executed: hook
Hook executed: hook
Task completed: background task
tasks__pause failed with "User does not own schedule" - interesting. Let me try update, get_results, and delete. Also image_to_video.
Hook executed: hook
Hook executed: hook
Hook executed: hook
Good. Now reference_to_video with both images, delete the MCP task, clean up sandbox, write results report.
Hook executed: hook
Hook executed: hook
Hook executed: hook
Now clean up the sandbox, write a RESULTS report inside it then delete the whole demo dir. Also complete todos.
Hook executed: hook
># Final sandbox state, then full cleanup
echo "=== Final sandbox tree ==="
find /tmp/grok-tool-demo.nhtuB3 -type f | sort
echo "=== sample.txt ==="
cat /tmp/grok-tool-demo.nhtuB3/src/sample.txt
echo "=== notes.md ==="
cat /tmp/grok-tool-demo.nhtuB3/src/notes.md
echo "=== Cleaning sandbox ==="
rm -rf /tmp/grok-tool-demo.nhtuB3
test ! -d /tmp/grok-tool-demo.nhtuB3 && echo "SANDBOX_REMOVED=ok" || echo "SANDBOX_REMOVED=fail"
# Confirm kill left nothing, scheduler empty already checked
echo "=== Done ==="Hook executed: hook
Hook executed: hook
Plan:
I've completed a comprehensive reversible demo. Let me summarize the results clearly for the user. Note that session media artifacts remain - I should mention that. Vercel MCP was unavailable due to a...
Sandbox: /tmp/grok-tool-demo.nhtuB3 (created → exercised → fully removed).
| Tool | Result |
|---|---|
run_terminal_command | Created sandbox + sample files |
list_dir | Listed src/, out/ |
read_file | Read sample.txt |
write | Created src/notes.md |
search_replace | Appended line 3 to sample.txt |
grep | Found hello / function matches |
| Cleanup | rm -rf sandbox → SANDBOX_REMOVED=ok |
| Tool | Result |
|---|---|
web_search | Found grok.com / x.ai |
open_page | Fetched example.com |
open_page_with_find | Pattern-matched “Example|documentation” |
web_fetch | Markdown for example.com |
x_user_search | Returned a user result |
x_keyword_search | Latest post related to xAI ecosystem |
x_semantic_search | Semantic hit on Grok announcement topic |
x_thread_fetch | Thread + replies for post 2072738598663946648 |
| Tool | Result |
|---|---|
| Background bash | 5-tick loop → completed, output retrieved |
get_command_or_subagent_output | Read ticks 1–5 + DONE |
Infinite loop + kill_command_or_subagent | Killed successfully |
monitor | Streamed monitor-event-1..3 + complete |
| Tool | Result |
|---|---|
scheduler_create | ID 019f6898f505 (one-shot, non-durable) |
scheduler_list | Showed the demo task |
scheduler_delete | Cancelled |
scheduler_list again | No scheduled tasks |
| Tool | Result |
|---|---|
todo_write | Tracked 5 demo steps (all completed) |
spawn_subagent (explore, read-only) | Confirmed tree, file contents, add() in math.js |
| Tool | Result |
|---|---|
search_tool | Discovered tasks + traces schemas |
tasks__create | Created tool-demo-reversible-test |
tasks__update | Renamed + updated prompt |
tasks__pause | Failed: “User does not own schedule” (gateway quirk) |
tasks__get_results | Failed: team ID mismatch |
tasks__delete | Archived successfully |
tasks__list | Empty after delete |
traces__traces_search | 2 recent traces (7d) |
traces__traces_read | Wrote markdown under sandbox out/ (removed with sandbox) |
| vercel | Not available (auth required) |
| Tool | Result |
|---|---|
image_gen | images/1.jpg (session) |
image_edit | images/2.jpg (session) |
image_to_video | videos/1.mp4 (session) |
reference_to_video | videos/2.mp4 (session) |
| Tool | Why skipped |
|---|---|
enter_plan_mode / exit_plan_mode | Switches the whole session into plan mode |
ask_user_question | Blocks for interactive input |
update_goal | Mutates goal-mode state |
Media lives under this session folder (not in your home/project tree):
images/1.jpg, images/2.jpgvideos/1.mp4, videos/2.mp4No scheduled tasks, no MCP demo task, no /tmp sandbox. Safe leftover only if you want to inspect the generated media.
Bottom line: Most tools exercised end-to-end with create→use→undo where applicable. Two MCP task APIs (pause, get_results) hit ownership/team errors; Vercel MCP needs auth.
System Reminder
Monitor "019f6899-4d24-7df1-9513-ca6a8de2c131" ended: [monitor ended: exited (code 0)].
Description: Short monitor event stream demo
Command: for i in 1 2 3; do echo "monitor-event-$i"; sleep 0.3; done; echo "monitor-complete"
Duration: 1.0s
Use get_command_or_subagent_output("019f6899-4d24-7df1-9513-ca6a8de2c131") for full output.The monitor completed successfully. This is just a system notification about the monitor ending. I already covered the monitor demo in my previous response. I don't need to do much - maybe briefly ack...
Monitor demo also finished cleanly (monitor-event-1..3 → monitor-complete, exit 0). That closes the last background piece from the reversible tool test — nothing else left running.
Hook executed: hook