A
licenseNot graded
qualityC
maintenanceProvides multimodal vision MCP tools for image analysis, OCR, object detection, text-to-image generation, and image similarity, integrating OpenAI, Qwen, and Gemini.
55 npm
1
MIT
pivision
by bliubliuing
Related Servers
Alternatives to pivision
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI-powered image generation and editing using Gemini and Imagen models, supporting text-to-image, image editing, and multi-image composition through MCP tools.MIT
- AlicenseAqualityDmaintenanceAllows AI assistants to generate and transform high-quality images from text prompts using Google's Gemini model via the MCP protocol.334MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI image processing tools such as vectorization, background removal, upscaling, and logo generation from any MCP-compatible client like Claude Code or Cursor.13 npmMIT
- FlicenseNot gradedqualityBmaintenanceEnables an AI assistant to generate and edit brand-compliant marketing images through MCP tools, including creating visuals from prompts, modifying reference photos, and refining results based on prior output.-
- FlicenseAqualityCmaintenanceEnables AI assistants to recognize and extract information from images via GLM-4V, supporting automatic screenshot recognition and MCP-based local image file reading for non-vision models like DeepSeek.1-
TDQS
A4.1/5.0
Scored across 6 tools
Disambiguation5/5
Each tool targets a distinct operation: image recognition (r-pic), video recognition (r-vid), general generation (g-pic), infographic generation (i-pic), image editing (p-pic), and batch execution (b-gen). Even g-pic and i-pic are clearly differentiated by their pipeline purpose and default models. There is no genuine overlap that would mislead an agent.
Naming Consistency4/5
All tools follow a consistent lowercase-with-hyphen abbreviation pattern (r-pic, r-vid, g-pic, i-pic, p-pic, b-gen), which makes the set feel uniform. However, the prefixes are cryptic and 'b-gen' breaks the '-pic/-vid' media suffix pattern slightly, so while predictable, the names are not immediately intuitive.
Tool Count5/5
Six tools is a well-scoped size for a multimodal vision server, covering recognition, generation, editing, and batch orchestration without unnecessary bloat. Each tool has a clear role, and the count feels appropriate for the stated domain.
Completeness5/5
The tool surface covers the core lifecycle of the vision domain: reading images and videos, generating images (general and infographic), editing images, and batching any of these tasks. There are no obvious missing operations that would block typical workflows for a vision and generation toolkit.
Maintenance
ActivityMaintained
ResponsivenessNo issues