impeccable
The design vocabulary for your coding agent. Steer with polish and bolder, review with critique and audit, catch AI slop before it ships.
Live 2D-to-3D stereo depth pipeline, Metal DIBR weaver, and MV-HEVC Spatial Video tool.
Skills that teach the AI this kind of work; they work alongside this one
The design vocabulary for your coding agent. Steer with polish and bolder, review with critique and audit, catch AI slop before it ships.
Editorial diagram design for Claude Code, Codex, GitHub Copilot, Cursor, Factory Droid, Qoder, and Pi. 45 diagram types. Self-contained HTML + SVG. No shadows. No Mermaid slop.
Create beautiful slides on the web using a coding agent's frontend skills
Lists are ordered by a usage score (out of 100) built from these parts
| Popularity | 0/80 | GitHub stars or weekly downloads: the larger counts 60, the smaller 20 |
|---|---|---|
| Freshness | 12/12 | Full marks for a release or code change within 30 days |
| Still answering | 0/8 | The cloud endpoint answered at the last check |
| Usage score | 12/100 |
Quality: Passed 2/3 basic checks (shown, not used for ordering) · Momentum: No data yet (Used only on the Trending tab)
Pick the AI app you use, then copy the settings.
Passed 2/3 checks · Runs on your computer
First: which AI do you use?
Pick your app and the steps appear below.
Works with Claude, with some setup first
No key, nothing to install · Only the Claude desktop app (Windows or Mac), not the web or phone
Download the maker’s .mcpb file
The .mcpb file comes straight from the maker; we do not change it
Use DepthPipe and tell me what you can do for me, then show me one thing✓ If Claude says it is using DepthPipe or shows a DepthPipe tool in the answer, you are connected
Menu names checked against Anthropic’s help page on Nov 11, 2026 · your screen may differ slightly by app version
ChatGPT cannot connect DepthPipe yet
DepthPipe runs on your computer, but ChatGPT can only connect servers that run on the web
A · Use an app that can connect DepthPipe
B · Others in Design, images & audio that work with ChatGPT
Picked from the most used in the same category, only ones that connect by address with no key
Claude Code cannot connect DepthPipe yet
The maker only provides an installer for the Claude desktop app
A · Use an app that can connect DepthPipe
Cursor cannot connect DepthPipe yet
The maker only provides an installer for the Claude desktop app
A · Use an app that can connect DepthPipe
VS Code cannot connect DepthPipe yet
The maker only provides an installer for the Claude desktop app
A · Use an app that can connect DepthPipe
DEPTHPIPE_LICENSE_KEY secret envDescriptions are as written by the maker.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
mcpb: …/depthpipe-0.1.0-macos-arm64.mcpbBased on how this server connects and on each app’s own docs, checked Nov 10, 2026.
Run on your computer in
ClaudeGooseLM StudioMsty StudioCherry StudioVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 22, 2026
The registry name was verified with the GitHub account raydeoliveira, which owns the repo
Code last changed today
GitHub could not identify the licence type; open the file to check
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Not checked: only npm and PyPI packages with a version can be checked
If you made this, paste this code into your README. The badge links back to this page.
[](https://mcp.popnx.com/en/servers/raydeoliveira-depthpipe)Ask, share a tip or report that it does not work. Sorted by what people marked helpful.
No posts yet. Be the first to ask or share.
Posts here are written by users, not the PopNx team.
No reviews yet
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 2 of 3 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed today, and the latest version (0.1.0) reached the registry today.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need MCPB on your computer.
In the same category: HyperFrames by HeyGen, Pascal 3D Editor, draw.io, Figma MCP Server, Remocn: Remotion MCP server
Same category, other makers, commands already checked. Official ones first, then by stars.
Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Official HyperFrames by HeyGen: the best AI video editor in chat. Captions, motion graphics, MP4.
Create, inspect, validate, and save editable 3D building scenes with Pascal's MCP server.
Create draw.io diagrams in chat from Mermaid or XML, shown live and interactive. 10,000+ shapes.
Figma’s official server gives AI your design data so it can turn designs into code or describe them accurately. Connects to Figma’s cloud.
Hosted MCP for Remotion videos: search Remocn components, read docs, plan a video, preview it.
| This one DepthPipe | HyperFrames by HeyGen | Pascal 3D Editor | draw.io | Figma MCP Server | Remocn: Remotion MCP server | |
|---|---|---|---|---|---|---|
| Runs where | Installs on your computer | Runs in the cloud, nothing to install | Cloud or install on your computer | Runs in the cloud, nothing to install | Runs in the cloud, nothing to install | Runs in the cloud, nothing to install |
| Needs a key | No | No | No | No | No | No |
| Add with + in Claude | No | Yes | No | No | Yes | No |
| Basic checks | 2/3 | 4/4 | 5/5 | 4/4 | 4/4 | 4/4 |
| License | NOASSERTION | Apache-2.0 | MIT | Apache-2.0 | – | MIT |
| Price | No cost listed in the registry | No cost listed in the registry | No cost listed in the registry | No cost listed in the registry | No cost listed in the registry | No cost listed in the registry |
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
Live 2D-to-3D stereo depth pipeline, runtime-compiled Metal DIBR synthesizer, bidirectional MV-HEVC Spatial Video converter, and SteamOS Vulkan Z-buffer implicit layer CLI and stdio MCP server (877,424 bytes / 857 KB stripped macOS arm64 binary, 7.00 ms min / 9.19 ms median --version cold start on Apple M4 Max, zero external Swift dependencies).
| Capability | Status | Notes / Requirements |
|---|---|---|
Hardware & media probing (probe, inspect) | Supported | Reports Metal GPU, VideoToolbox MV-HEVC encode/decode, ScreenCaptureKit TCC, and CoreML status; parses ISO BMFF hvcC, lhvC, and vexu boxes |
Game Depth Profile catalog (profile, profiles) | Supported | 13 deterministic profiles (near_plane, far_plane, disparity_px, convergence_px, depth_invert, reversed_z) keyed by Steam AppID or bundle ID |
Metal DIBR & stereo weaving (render) | Supported | Runtime-compiled MSL compute kernels (rgbd_dibr_synthesize, split_packed_stereo, shift_stereo_convergence, weave_stereo_pair) across 8 PNG output layouts (full-sbs, half-sbs, tab, row-interlaced, col-interlaced, checkerboard, lenticular, dubois-anaglyph) |
Bidirectional MV-HEVC video (convert) | Supported | Audio-preserving VideoToolbox MV-HEVC .mov <-> Full-SBS/Half-SBS/TAB/interlaced/anaglyph .mov/.mp4 |
Live capture & sim fixtures (capture) | Supported | ScreenCaptureKit 32BGRA capture (gated by CGPreflightScreenCaptureAccess(), exit 4 on denial) plus --sim --fixture (gradient-shapes, checker-fg, portrait-card, desktop-sim, desktop-pillar) |
SteamOS Vulkan Z-buffer layer (vulkan-layer/) | Linux source + macOS unit-tested | Builds libVkLayer_depthpipe_zbuf.so + VkLayer_depthpipe_zbuf.json + shaders/dibr_zbuf.comp on Linux/SteamOS; verified on macOS via clang++ -std=c++20 ASan+UBSan unit, CPU parity, and regression tests against minimal Khronos ABI types (not a macOS MoltenVK ICD layer) |
| Neural weights & FFmpeg | Not bundled | Omit --model for built-in Metal synthetic depth, or supply --model for CoreML ANE inference; zero bundled FFmpeg binaries |
# Build from source (Commercial edition)
cd projects/depthpipe
brew install raydeoliveira/tap/depthpipe
Build and test the SteamOS Vulkan layer on Linux/SteamOS (or run its C++20 ASan+UBSan tests on macOS):
make -C projects/depthpipe/vulkan-layer clean all test
Linux Vulkan layer environment variables: DEPTHPIPE_VK_ENABLE=1, DEPTHPIPE_VK_DISABLE=1, DEPTHPIPE_BYPASS=1, DEPTHPIPE_NEAR_PLANE, DEPTHPIPE_FAR_PLANE, DEPTHPIPE_DISPARITY_PX, DEPTHPIPE_CONVERGENCE_PX, DEPTHPIPE_REVERSED_Z, DEPTHPIPE_DEPTH_INVERT.
To uninstall:
brew uninstall depthpipe
rm -rf ~/.config/depthpipe
--json Agent Usage)$ depthpipe --version
depthpipe 0.1.0 (commercial, arm64)
$ depthpipe probe --json {"data":{"capture_backend":"ScreenCaptureKit","coreml_available":true,"gpu_available":true,"gpu_backend":"Metal","gpu_name":"Apple M4 Max","metal_available":true,"mv_hevc_decode_supported":true,"mv_hevc_encode_supported":true,"screen_capture_permitted":true},"error":null,"ok":true,"schema_version":1}
$ depthpipe profile --app 1091500 --json {"data":{"aliases":["com.cdprojektred.cyberpunk2077","cyberpunk2077"],"app_id":"1091500","convergence_px":0,"depth_invert":false,"disparity_px":26,"far_plane":1000,"id":"cyberpunk-2077","matched":true,"near_plane":0.1,"notes":"REDengine 4 reversed-Z float32 depth buffer; moderate convergence for indoor HUD.","reversed_z":true,"title":"Cyberpunk 2077"},"error":null,"ok":true,"schema_version":1}
$ depthpipe capture --sim --fixture gradient-shapes --max-frames 2 --out-layout full-sbs --output /tmp/dp_cap.png --dry-run --json {"data":{"depth_source":"metal-synthetic","elapsed_ms":0,"fixture_name":"gradient-shapes","frames_captured":0,"frames_processed":0,"gpu_name":"Apple M4 Max","media_artifact":{"eye_height":240,"eye_width":320,"frames_processed":0,"out_layout":"full-sbs","output_height":240,"output_path":"/tmp/dp_cap.png","output_width":640},"source":{"bundle_id":"com.depthpipe.sim","height":240,"kind":"sim","source_id":1,"title":"Simulated Spatial Desktop (320x240)","width":320},"used_sim":true},"error":null,"ok":true,"schema_version":1}
$ edidsmith edid budget --width 3840 --height 1080 --hz 60 --link usbc-4lane --json \ | depthpipe render --input frame.png --output frame_sbs.png --out-layout full-sbs --from-json - --json \ | glassweave weave --output woven.png --from-json - --json
capture without --sim or --fixture calls CGPreflightScreenCaptureAccess() first and exits 4 with System Settings > Privacy & Security > Screen Recording instructions when denied.render, convert, and capture refuse overlapping input/output or colliding --output/--depth-out paths (including resolved symlinks and case-variants) with exit 2; HEVC 4:2:0 video outputs reject odd or < 2x2 dimensions with exit 2.--output or --depth-out file fails closed (exit 2) unless --yes is passed; writing to a new output file in a pipe works without --yes.ok: false or solved_mode.fits == false (BANDWIDTH_EXCEEDED) aborts immediately with exit 2.sigaction (sa_flags = 0) for SIGINT and SIGTERM, exiting 130.0: Success1: Runtime, GPU, capture, or media failure2: Invalid usage, NaN/Inf/odd dimensions, non-TTY overwrite without --yes, BANDWIDTH_EXCEEDED, or upstream --from-json ok: false3: Metal GPU or capture source unavailable4: Screen Recording TCC permission denied130: SIGINT or SIGTERM receivedRun depthpipe --help for human CLI usage, depthpipe --describe for the JSON capability manifest, or depthpipe mcp for stdio JSON-RPC 2.0 (2024-11-05) MCP tools (probe_pipeline, lookup_depth_profile, inspect_media, render_stereo, convert_media, capture_frames).