Skip to main content
Glama
Sign In
mcp-vision

mcp-vision

by MikeyBeez
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

mcp-vision

MCP server for vision capabilities - screenshot and camera analysis using Ollama vision models.

Features

  • Screenshot Analysis: Capture and analyze screenshots with AI

  • Camera Capture: Take photos from webcam and analyze them

  • Image Analysis: Analyze existing image files

  • Streaming Output: Real-time streaming of AI analysis

  • Multiple Models: Support for various vision models (llava, bakllava, etc.)

Related MCP server: ollama-vision-mcp

Installation

cd /Users/bard/Code/mcp-vision
npm install

Prerequisites

  • Ollama must be running with a vision model installed:

    ollama pull llava

  • macOS (for screenshot functionality)

  • Camera access (for webcam features)

Tools

vision_screenshot

Take a screenshot and analyze it with AI.

{
  prompt: "What application is open?",  // optional
  model: "llava",                       // optional
  region: {                             // optional
    x: 100,
    y: 100,
    width: 500,
    height: 400
  }
}

vision_camera

Capture from camera and analyze.

{
  prompt: "What do you see?",  // optional
  model: "llava",              // optional
  device: "FaceTime HD Camera" // optional
}

vision_analyze_image

Analyze an existing image file.

{
  path: "/path/to/image.jpg",
  prompt: "Describe this image",  // optional
  model: "llava"                  // optional
}

vision_list_cameras

List available camera devices.

Usage with Claude Desktop

Add to your Claude Desktop configuration:

{
  "mcpServers": {
    "vision": {
      "command": "node",
      "args": ["/Users/bard/Code/mcp-vision/src/index.js"]
    }
  }
}

Integration with ELVIS

This tool can be integrated with ELVIS for enhanced visual context:

  1. Use vision_screenshot to capture current screen state

  2. Pass the analysis to elvis_delegate for context-aware task processing

  3. ELVIS can use visual information to better understand and complete tasks

Example Workflow

// 1. Analyze what's on screen
vision_screenshot({ prompt: "What code is visible?" })

// 2. Use with ELVIS
elvis_delegate({ 
  task: "Fix the syntax error shown",
  context: "Based on the screenshot analysis"
})

Streaming Output

The tool streams AI responses in real-time, providing immediate feedback as the model analyzes images. This is shown in the MCP server logs and can be used for progress tracking.

Available Tools

4 tools
helpA

Get comprehensive documentation for all vision functions

Inputs: no named parameters.

vision_analyze_imageB

Analyze an image file with Ollama vision model

Inputs: path (required), model, prompt.

vision_cameraC

Take a photo with camera and analyze it

Inputs: model, prompt.

vision_screenshotB

Take a screenshot and analyze it with Ollama vision model

Inputs: model, prompt.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A3.5/5.0

    Scored across 4 tools

    Disambiguation5/5

    Each tool targets a distinct input source: screenshot captures the screen, camera captures from a physical camera, and analyze_image works with existing files. The help tool is clearly auxiliary and separate from the vision functions.

    Naming Consistency3/5

    Three tools share a 'vision_' prefix, but the structure varies: 'screenshot' and 'camera' are single nouns used as verbs, while 'analyze_image' follows verb_noun. The 'help' tool breaks the prefix pattern entirely, making the naming inconsistent.

    Tool Count5/5

    With four tools, the server is well-scoped for its purpose. It covers the three primary vision input methods (screen, camera, file) plus documentation, with no redundancy or unnecessary bloat.

    Completeness4/5

    The core vision analysis workflows are covered: capturing and analyzing from screen or camera, and analyzing existing images. However, there are minor gaps such as no way to capture an image without analysis, no model management, and no URL-based image input, though these are not critical for the server's stated purpose.

    Resources

    Related MCP Connectors

    Related MCP Servers

    • llm-vision-mcp

      ghbalf
      A
      license
      Not graded
      quality
      D
      maintenance
      An MCP server that enables any LLM to describe images from file paths, URLs, or base64 data by forwarding them to a supported vision provider such as OpenAI, Anthropic, or local Ollama models.
      396 npm
      10
      MIT

    • ollama-vision-mcp

      ducnm9
      F
      license
      A
      quality
      D
      maintenance
      MCP server enabling LLM clients without vision capability to process images by delegating to local Ollama vision models. Supports describing images, OCR, asking questions, and processing clipboard images.
      4
      -

    • pic-id-mcp

      HaoyueQin
      A
      license
      Not graded
      quality
      C
      maintenance
      Local vision-capable MCP server that lets AI agents describe screenshots, UI, charts, and photos via vision and OCR tools, with support for multiple providers and automatic fallback.
      5
      MIT

    • local-vision-mcp

      tmchao7
      A
      license
      Not graded
      quality
      B
      maintenance
      MCP server for local Ollama vision analysis, enabling text-only agents like Claude Code to inspect images via a single tool. Processes images locally with Ollama, keeping image bytes on the machine and returning text reports.
      2
      MIT