Pinterest Vision Mcp

devops-infra MCP Server

Visual intelligence pipeline for AI agents — search Pinterest, analyze with LLM vision, store and retrieve by semantic similarity

Verified
devops-infradevops-infra
6 views1 stars0 forks

Why This Matters

Discovered via github-topic:mcp-server and last synced 2mo ago.

Verified
Source
github-topic:mcp-server
Stars
1
Last synced
2mo ago
Install
Check source

Install

Install instructions not detected yet

Check the source repository for the latest setup steps.

View source instructions
27
Tools
0
Resources
0
Prompts
Standard I/O
Transport

Available Tools (27)

lighting_type

natural, studio, golden hour, overcast

overall_quality

reference-worthy / average / not useful

shot_type

campaign editorial / e-commerce product / lookbook

segment

luxury / premium / contemporary / streetwear

VISION_API_KEY

garment_focus

clothing items featured

visual_search

Semantic search across stored visual references

camera_distance

close-up, medium, full body, detail shot

palette

free-text color description

Tag

Example values

styling_signals

styling details and accessories

brand_feel

brand aesthetic impression

VISION_API_BASE_URL

`https://openrouter.ai/api/v1`

pinterest_ingest

Store analyses in ChromaDB for semantic retrieval

pinterest_analyze

Analyze images with LLM vision — returns structured aesthetic tags

mood

editorial, minimal, dark, romantic, energetic

raw_description

2–3 sentence summary

Tool

Description

Variable

Default

PINTEREST_VISION_MODEL

`anthropic/claude-sonnet-4-6`

pinterest_pipeline

Full pipeline in one call: search → download → analyze → store

PINTEREST_DATA_DIR

`./data`

CHROMA_PERSIST_DIR

`./data/chroma`

Field

Example values

composition_type

centered, rule-of-thirds, flat lay, symmetrical

pinterest_search

Search Pinterest by query — returns pins with image URLs

pinterest_download

Download images from search results to local disk