BlueVetaUpright MCP server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@BlueVetaUpright MCP server Is this product photo sideways? https://cdn.shop.com/shoe.jpg"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
BlueVetaUpright MCP server
An MCP server that gives any MCP-compatible AI client
(Claude Desktop, and any other MCP-aware agent) a detect_rotation tool: checks whether a
product photo is upright and, if not, exactly how many degrees to rotate it.
How billing works (read this first)
This server is a thin wrapper around the real, paid BlueVetaUpright API
(https://blueveta.com/api/upright/detect). It is bring-your-own-key (BYOK): every call
bills your own BlueVetaUpright account, exactly the same as calling the REST API directly.
There is no free tier hiding behind this tool — get a key and credits at
blueveta.com/upright.
Related MCP server: pictor-mcp
Install & configure
npm installSet your API key as an environment variable (recommended — configure it once in your MCP client's server config, not per call):
export BLUEVETA_UPRIGHT_API_KEY=bvu_live_...Then point your MCP client at node src/server.js (stdio transport) in this directory. A
call can also override the key per-invocation with an apiKey argument if that fits your
client's auth model better than an environment variable.
The tool
detect_rotation(imageUrl | imageBase64, returnImage?, apiKey?) → the same response shape
as the REST API: wasAlreadyUpright, rotationClockwise4Axis, confidence4Axis,
rotationClockwiseFull, confidenceFull, resolved, note, and (when returnImage: true,
priced 1.5x same as the REST API) imageBase64/imageMimeType of the corrected photo.
Development
npm testRuns detectRotation.js's own unit tests — the core HTTP-calling logic (which endpoint,
whose key, what gets sent) is dependency-free and tested with a mocked fetch, independent
of the MCP SDK wiring in server.js.
Status
Built and unit-tested (2026-10-29). Published to npm as
blueveta-upright-mcp
(v0.1.0, 2026-11-19) and listed on the official
MCP Registry as
com.blueveta/upright — genuinely installable via npx blueveta-upright-mcp,
not just a registry listing. See .claude/rules/upright.md item 26 for the
current real status.
Available Tools
1 tooldetect_rotationDetect and fix a product photo's rotationA
Checks whether a product photo is upright and, if not, exactly how many degrees to rotate it (clockwise). Returns a confidence score and an honest flag when the answer is uncertain. Bills the caller's own BlueVetaUpright account per call, same as the REST API -- requires an API key from https://blueveta.com/upright, set as BLUEVETA_UPRIGHT_API_KEY or passed as apiKey.
Inputs: apiKey, imageUrl, imageBase64, returnImage.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
There is only one tool, so there is no possibility of misselection or overlap. The tool's stated purpose (upright/rotation-angle detection with confidence and uncertainty flagging) is unambiguous.
detect_rotation follows a clear verb_noun snake_case convention. With a single tool there is no risk of mixed conventions, so the set is trivially consistent.
One tool is thin for a server surface, but the declared domain is genuinely narrow (rotation detection only), so it is borderline rather than a clear mismatch. It lands at the 'feels thin' level rather than being grossly under- or over-scoped.
The detection operation itself is well covered (angle, confidence, uncertainty flag, auth/billing notes), but there are notable gaps: no batch/multi-image handling, no tool to apply the rotation or return a corrected image, and no usage or quota check. Agents can work around these but will hit a dead end for any follow-on step.
Maintenance
Related MCP Connectors
Run AI-powered analysis on images including moderation, captioning, tagging, and more.
AI product photography for fashion sellers: Shopify photo audits, seasonal guides, AI try-on.
Check and fix Amazon, eBay and Etsy product images, calculate marketplace fees, look up barcodes.
On-model and ghost-mannequin fashion photos from a product photo. Spends credits; needs an API key.
Related MCP Servers
- FlicenseAqualityDmaintenanceMCP server for image analysis, providing OCR text extraction, image metadata, and EXIF/GPS data as structured JSON for downstream processing.3-
- AlicenseAqualityBmaintenanceEnables MCP clients to inspect, convert, resize, compress, crop, rotate, watermark, background-remove, and batch-process images with secure path confinement and result verification.14MIT
- AlicenseAqualityBmaintenancefixRAgent, by AR Logic LLC, turns one photo of a building problem into what it is, how urgent it is (EMERGENCY, TODAY, THIS WEEK or WHENEVER), which trade to call, and what to tell the resident. For property managers, landlords and companies. NARPM member. Free Test Drive for up to 10 doors; paid plans from $39/mo. fixragent.com/pricing Remote MCP server: fixragent.com/mcp3MIT
- AlicenseNot gradedqualityCmaintenanceEnables agents to run checklist-driven e-commerce image quality inspection with auditable local rules, returning pass/needs-work/fail verdicts, actionable fixes, SKU consistency checks, report files, threshold advice from reviewer overrides, and token cost estimates.MIT