nvidia-app
NVIDIA App MCP: drivers, games, laptops, overlay.
Skill by NVIDIA CORPORATION <info@nvidia.com>
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/nvidia-nvidia-app
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building, monitoring-observability
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/nvidia-app
What's inside
- Skill name
nvidia-app- Description
- NVIDIA App MCP: drivers, games, laptops, overlay. Check drivers, manage and optimize games, configure laptop features.
- License
- Apache-2.0
- Metadata
- team: nvidia-app · author: NVIDIA CORPORATION <info@nvidia.com> · domain: system-tools · version: 1.1.8
- Instructions
- 211 lines in SKILL.md · view on GitHub
Files (10)
- BENCHMARK.md
- SKILL.md
- evals.json · evals/
- connection.md · references/
- general-tools.md · references/
- mcp-tool-contract.md · references/
- overlay-capture.md · references/
- overlay-state.md · references/
- skill-card.md
- skill.oms.sig
SKILL.md (first lines)
# NVIDIA App MCP Overlay
## Purpose
Use this skill for one product integration: operating NVIDIA App through its local MCP server. It has two routed modes:
- General NVIDIA App operations cover application listing and launch, driver status and release notes, per-game optimization, and laptop features.
- In-Game Overlay operations use the workflow below.
The Overlay workflow supports:
- Read high-level Overlay status.
- Start or stop gameplay recording.
- Enable, disable, or save Instant Replay.
- Enable or disable Highlights.
- Capture a screenshot to the Overlay gallery.
- Show or hide the Statistics Overlay.
- Enable or disable the RTX Dynamic Vibrance filter.
- Identify the currently running game.
Connection setup supports both modes but does not authorize additional actions.
## When to use this skill
Use this skill when the user asks for one of the supported application, driver, game-optimization, laptop-feature, Overlay, or connection workflows.
Do not select this skill for Desktop Capture, other Overlay filter mutations, NVIDIA Broadcast, OBS, Xbox Game Bar, or other capture software.
## Inputs
- **Required:** A user request for a supported NVIDIA App query, mutation, or connection diagnostic.
- **Optional:** An explicit target state, game or program identifier, tool-specific values, and client connection details. Obtain authentication tokens only from the protected discovery source described in [references/connection.md](references/connection.md); never accept or expose them as ordinary tool arguments.
Resolve information in this order: explicit user instructions, fresh live MCP schema or state, current client connection configuration, then the applicable self-contained skill reference for static contract details. Never treat a previous tool result as current state.
## Prerequisites
- Windows host with NVIDIA App installed (version 11.0.9.5xx or above) and its NvContainer-hosted MCP plugin running.
- Standard NVIDIA App executable path: `%ProgramFiles%\NVIDIA Corporation\NVIDIA App\CEF\NVIDIA App.exe`.
- MCP server access is enabled when NVIDIA App exposes a master toggle.
- NVIDIA In-Game Overlay is enabled, running, and ready before any `nvapp_overlay_` call.
- The MCP client supports Streamable HTTP over loopback or connects through the installed stdio bridge.
MCP server readiness and Overlay readiness are separate. A successful MCP connection does not establish that Overlay tools are ready.
## Instructions
1. **Classify the request.** Route general NVIDIA App requests through live tool discovery. Route `nvapp_overlay_` requests through the Overlay workflow. Read-only Overlay status can include fields for excluded features, but that does not authorize changing them.
2. **Register `nvidia-app` in the current MCP client, or fall back explicitly.** The client is registered only when this session's live tool catalog advertises `nvapp_` tools; an open loopback port or a working stdio bridge is not registration. If those tools are absent, attempt registration per [references/connection.md](references/connection.md) before the first `nvapp_` call. Registration is the default path because it persists across turns and sessions. A reachable HTTP endpoint is not a reason to skip the attempt.
3. **Use the direct connection only as a declared fallback.** If the user declines the configuration change, the client cannot be modified or reloaded, or registration succeeds but `nvapp_` tools still do not appear in this session, connect directly to the loopback HTTP endpoint (or the stdio bridge) and continue with the same documented tool contracts. Say which path you used and that registering `nvidia-app` would make access persistent. Do not silently prefer the direct path.
4. **Discover general tools.** For a non-Overlay request, inspect `tools/list` on whichever connection you established, then read [references/general-tools.md](references/general-tools.md) before selecting or calling one of its seven documented public tools. Select only a returned tool whose description, schema, and annotations most narrowly match the user's in-scope intent, and follow any narrower live schema and annotations.
5. **Resolve an Overlay target state.** For an explicit start, stop, enable, disable, show, or hide request, call the mapped mutation directly. For a true toggle with no target state, read status once and invert only the corresponding Boolean.
6. **Validate the arguments.** For general tools, follow [references/general-tools.md](references/general-tools.md) and any narrower live schema. For Overlay tools, use exactly the mapped fields below. Never invent unsupported arguments.
7. **Execute in request order.** Fulfill compound requests by issuing each supported operation as its own tool call in the user's order. Make only the calls needed for the requested operations. Respect the access tier and any consent decision; never raise access or enable another feature as a workaround.
8. **Interpret the result literally.** Report only returned fields and outcomes. Overlay mutations return a human-readable message; report that message without inventing structured success fields. If a mutation message is ambiguous, state that the outcome is not independently confirmed instead of making a follow-up Overlay status call solely to verify it.
## Connecting
The default HTTP endpoint is:
```text
http://127.0.0.1:13508/mcp
```
The installed stdio bridge is:
```text
%ProgramFiles%\NVIDIA Corporation\NVIDIA App\McpServer\NvAppMcpServer.exe
```
The stdio executable relays to the persistent server; it does not start or enable that server.
## General NVIDIA App operations
Read [references/general-tools.md](references/general-tools.md) before selecting or calling a general NVIDIA App tool. It contains the seven supported tool names, exact arguments, enums, conditional schemas, and prerequisite checks.
Use only a documented tool advertised by live `tools/list`. The packaged instructions are self-contained and do not depend on repository-internal schema sources.
## Overlay operations
Use only the tools in this table and the authorized arguments shown here:
| User intent | Tool | Arguments |
|---|---|---|
| Read overall Overlay status | `nvapp_overlay_get_status` | `{}` |
| Start recording | `nvapp_overlay_capture` | `{ "action": "toggle_recording", "enable": true }` |
| Stop and save recording | `nvapp_overlay_capture` | `{ "action": "toggle_recording", "enable": false }` |
| Enable Instant Replay | `nvapp_overlay_capture` | `{ "action": "toggle_instant_replay", "enable": true }` |
| Disable Instant Replay | `nvapp_overlay_capture` | `{ "action": "toggle_instant_replay", "enable": false }` |
| Save Instant Replay | `nvapp_overlay_capture` | `{ "action": "save_instant_replay" }` |
| Enable Highlights | `nvapp_overlay_capture` | `{ "action": "toggle_highlights", "enable": true }` |
| Disable Highlights | `nvapp_overlay_capture` | `{ "action": "toggle_highlights", "enable": false }` |
| Capture a screenshot | `nvapp_overlay_capture` | `{ "action": "capture_screenshot" }` |
| Show Statistics Overlay | `nvapp_overlay_configure_stats` | `{ "enable": true }` |
| Hide Statistics Overlay | `nvapp_overlay_configure_stats` | `{ "enable": false }` |
| Enable RTX Dynamic Vibrance | `nvapp_overlay_configure_filters` | `{ "filter": "rtx_dvc", "enable": true }` |
| Disable RTX Dynamic Vibrance | `nvapp_overlay_configure_filters` | `{ "filter": "rtx_dvc", "enable": false }` |
| Get current game | `nvapp_overlay_get_current_game_info` | `{}` |
Never invoke `toggle_desktop_capture`. For `nvapp_overlay_configure_filters`, use only the `rtx_dvc` filter value.
## Capture and privacy
`toggle_recording`, `toggle_instant_replay`, `save_instant_replay`, `toggle_highlights`, and `capture_screenshot` record screen content and write media files to the user's system. Recordings and screenshots persist in the NVIDIA App Overlay gallery until the user deletes them, and this skill cannot choose their format, resolution, or destination.
Treat every one of them as a privacy-affecting operation:
- An explicit user request to start, stop, save, enable, or capture is the authorization. Make that single mapped call without an additional confirmation prompt, then report the returned message so the user knows capture began or media was written.
- Never initiate capture the user did not ask for. Do not start recording as a side effect of another request or as a workaround for a failed operation.
- Ask first when the request is ambiguous, when a true toggle has no target state and the status field is missing, or when an unsupported qualifier such as a format or destination applies.
- Enabling Instant Replay or Highlights leaves background capture running until it is disabled. Say so when you enable either one.
- Do not enable Desktop Capture to make a capture succeed. Content outside a supported game stays out of scope for this skill.
## Decision rules
- If this session's MCP catalog has no `nvapp_` tools, attempt `nvidia-app` registration before connecting directly. Once registration is refused or has failed, a direct HTTP or stdio connection is allowed for the rest of the session without re-asking.From NVIDIA/skills, Apache-2.0.
More from NVIDIA/skills
- 0.846score
jetson-video-recipe
Vinit Bansal <vinitkumarb@nvidia.com>
Use when turning a Jetson encoder use case into one surface-neutral recipe with native Video Codec SDK and PyNvVideoCodec projections.
SkillAFreshness: A★ 3.7KClaude Code +9 - 0.846score
jetson-video-pipeline
Vinit Bansal <vinitkumarb@nvidia.com>
Use when planning, executing, and independently validating Jetson Video Codec SDK or PyNvVideoCodec encode/decode, transcode, segmentation, container decode…
SkillAFreshness: A★ 3.7KClaude Code +9 - 0.846score
nvflare-convert-lightning
NVIDIA FLARE Team <federatedlearning@nvidia.com>
Convert existing PyTorch Lightning training code into an NVFLARE federated job using the Lightning Client API patch, local validation, and job export; use…
SkillAFreshness: A★ 3.7KClaude Code +9 - 0.846score
nemo-fabric-integrate
NVIDIA Corporation and Affiliates
Use this skill when integrating NVIDIA NeMo Fabric into a consumer application, service, evaluation harness, or platform through the typed Python SDK —…
SkillAFreshness: A★ 3.7KClaude Code +9 - 0.846score
nvflare-diagnose-job
NVIDIA FLARE Team <federatedlearning@nvidia.com>
Use when the user asks why a reported NVFLARE job failure signal occurred: the job failed, stalled, timed out, lost clients, ended with EXECUTION_EXCEPTION…
SkillAFreshness: A★ 3.7KClaude Code +9 - 0.846score
nvflare-fed-stats
NVIDIA FLARE Team <federatedlearning@nvidia.com>
Compute federated statistics over tabular data (count, sum, mean, stddev, var, histogram, quantile, noise-protected min/max) and image data (count…
SkillAFreshness: A★ 3.7KClaude Code +9 - 0.846score
jetson-video-setup
Vinit Bansal <vinitkumarb@nvidia.com>
Use when installing, repairing, reusing, inspecting, or verifying readiness of the native NVIDIA Video Codec SDK or PyNvVideoCodec on Jetson, including the…
SkillAFreshness: A★ 3.7KClaude Code +9 - 0.846score
nvflare-convert-pytorch
NVIDIA FLARE Team <federatedlearning@nvidia.com>
Convert existing plain or manual PyTorch training code into an NVFLARE federated job using Client API model exchange, local validation, and job export; use…
SkillAFreshness: A★ 3.7KClaude Code +9 - 0.846score
nemo-relay-install
NVIDIA Corporation and Affiliates
Use this skill when choosing or running NeMo Relay installation for an agent runtime, application language, framework integration, or plugin bundle, or…
SkillAFreshness: A★ 3.7KClaude Code +9 - 0.846score
nemo-relay-get-started
NVIDIA Corporation and Affiliates
Use this skill when first-time NeMo Relay users want help selecting and following an appropriate quick-start guide or verifying their first working integration.
SkillAFreshness: A★ 3.7KClaude Code +9 - 0.846score
nvidia-broadcast
NVIDIA Broadcast Team <broadcast-skills-dev@nvidia.com>
Use when controlling NVIDIA Broadcast through MCP to apply effects, process local media, select devices, or change camera resolution, or when Broadcast is…
SkillAFreshness: A★ 3.7KClaude Code +9 - 0.846score
jetson-video-capability
Vinit Bansal <vinitkumarb@nvidia.com>
Use when Jetson codec, profile, chroma, bit-depth, dimension, engine-count, or operational support must be reconciled from live APIs, authenticated NVIDIA…
SkillAFreshness: A★ 3.7KClaude Code +9
Signals
- Stars
- 3,718
- Forks
- 457
- Open issues
- 8
- Last commit (this folder)
- Oct 2, 2026 (26 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- Version
- 1.1.8
- License
- Apache-2.0
- Repository
- github.com/NVIDIA/skills
- Website
- docs.nvidia.com/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from NVIDIA CORPORATION <info@nvidia.com>
Cite this page
nvidia-app skill. Agent Mart. https://agentmart.dev/skills/nvidia-nvidia-app (last updated 2026-10-24)