Which integrations are available for this server?

Provides image description and object detection with bounding boxes using Gemini vision models through Google Cloud's Vertex AI, enabling AI agents to analyze images and locate objects within them. Provides image description capabilities using OpenAI's vision models, enabling AI agents to analyze and understand images.

How do I use mcp-see?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@mcp-see describe this UI screenshot and extract button colors" 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.

mcp-see

by simen

Overview Schema Related Servers Score Discussions

TypeScript

Hybrid

mcp-see

An MCP server that gives AI agents eyes - the ability to observe and understand images without stuffing raw pixels into their context window.

Features

Multi-provider vision: Describe images using Gemini, OpenAI, or Claude
Object detection: Find objects with bounding boxes (Gemini)
Hierarchical analysis: Detect regions, then zoom in for detail
Precise color extraction: K-Means clustering in LAB color space
Color naming: Human-readable color names via color.pizza API

Installation

Run directly from GitHub with npx:

npx github:simen/mcp-see

Or clone and build locally:

git clone https://github.com/simen/mcp-see.git
cd mcp-see
npm install
npm run build

MCP Client Configuration

Claude Desktop

Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):

{
  "mcpServers": {
    "mcp-see": {
      "command": "npx",
      "args": ["github:simen/mcp-see"],
      "env": {
        "GOOGLE_CLOUD_PROJECT": "your-project-id",
        "OPENAI_API_KEY": "sk-...",
        "ANTHROPIC_API_KEY": "sk-ant-..."
      }
    }
  }
}

Other MCP Clients

The server runs on stdio transport. Configure your client to spawn npx github:simen/mcp-see.

Tools

`describe`

Get an AI-generated description of an image.

Input:

{
  "image": "/path/to/image.png",
  "prompt": "What is shown in this image?",
  "provider": "gemini",
  "detail": "detailed"
}

Example Output:

The image shows a vibrant and colorful salad bowl, viewed from directly above.
The bowl is made of a light brown, possibly biodegradable material. The salad
is composed of various ingredients arranged in distinct sections: two small
white peeled eggs, sliced red tomatoes topped with chopped green onions, cubed
seasoned tofu, bright green edamame beans, shredded purple cabbage, and
julienned carrots...

`detect`

Detect objects and return bounding boxes. Uses Gemini for native bbox support.

Input:

{
  "image": "/path/to/image.png",
  "prompt": "find all TV screens"
}

Example Output:

{
  "count": 3,
  "objects": [
    { "id": 1, "label": "television", "bbox": [178, 245, 433, 818] },
    { "id": 2, "label": "television", "bbox": [614, 518, 792, 898] },
    { "id": 3, "label": "television", "bbox": [617, 198, 792, 493] }
  ]
}

Coordinates are [ymin, xmin, ymax, xmax] normalized 0-1000.

`describe_region`

Crop to a bounding box and describe that region in detail.

Input:

{
  "image": "/path/to/image.png",
  "bbox": [200, 200, 800, 800],
  "prompt": "describe this in detail",
  "provider": "gemini"
}

Example Output:

{
  "bbox": [200, 200, 800, 800],
  "description": "The image showcases a vibrant and colorful salad bowl in close-up. The bowl contains fresh ingredients including cubed tofu with a seasoned exterior, bright green edamame, sliced tomatoes, and shredded purple cabbage..."
}

`analyze_colors`

Extract dominant colors from a region using K-Means clustering in LAB color space.

Input:

{
  "image": "/path/to/image.png",
  "bbox": [100, 200, 400, 600],
  "top": 5
}

Example Output:

{
  "dominant": [
    {
      "hex": "#e6e6e5",
      "rgb": [230, 230, 229],
      "hsl": { "h": 60, "s": 2, "l": 90 },
      "name": "Ambience White",
      "percentage": 75.91
    },
    {
      "hex": "#b16c39",
      "rgb": [177, 108, 57],
      "hsl": { "h": 26, "s": 51, "l": 46 },
      "name": "Ginger Dough",
      "percentage": 15.91
    }
  ],
  "average": {
    "hex": "#c4b8a8",
    "rgb": [196, 184, 168],
    "name": "Doeskin"
  },
  "confidence": "high",
  "region": {
    "bbox": [100, 200, 400, 600],
    "size": [200, 150],
    "totalPixels": 30000
  }
}

The confidence field indicates color precision:

high: Flat colors (UI elements) - clusters are tight
medium: Mixed content
low: Photographs/gradients - colors are approximate

Workflows

Hierarchical Image Understanding

The power of mcp-see is in combining tools for progressive analysis:

1. describe(image)
   → "A shelf displaying various vintage electronics and TVs"

2. detect(image, "find all screens")
   → [{label: "television", bbox: [178, 245, 433, 818]}, ...]

3. describe_region(image, [178, 245, 433, 818])
   → "A vintage CRT television with wood grain casing, displaying
      a test pattern. The screen shows horizontal color bars..."

4. analyze_colors(image, [178, 245, 433, 818])
   → dominant: ["#2b1810" Espresso Bean, "#c4a882" Sandcastle, ...]

Design Reference Analysis

Extract implementation-ready specs from design mockups:

1. describe(image, "explain this UI to a web developer")
   → Layout structure, component hierarchy, spacing patterns

2. detect(image, "find all buttons")
   → Bounding boxes for each button

3. For each button:
   - describe_region() → Button label, icon, state
   - analyze_colors() → Exact color tokens for CSS

Environment Variables

Variable	Description	Required
`GOOGLE_CLOUD_PROJECT`	GCP project ID for Vertex AI	For Gemini
`OPENAI_API_KEY`	OpenAI API key	For OpenAI provider
`ANTHROPIC_API_KEY`	Anthropic API key	For Claude provider

Gemini uses Google Cloud Application Default Credentials (ADC). Run gcloud auth application-default login to authenticate.

Technical Details

Color Extraction Algorithm

The analyze_colors tool uses K-Means clustering in LAB color space:

Convert pixels from RGB to LAB (perceptually uniform)
Subsample to 50k pixels for performance
K-Means++ initialization for better convergence
Cluster centroids become dominant colors
Convert back to RGB, name via color.pizza API

This approach groups perceptually similar colors together, working well for both flat UI colors and noisy photographs.

Bounding Box Format

All bounding boxes use [ymin, xmin, ymax, xmax] format with coordinates normalized to 0-1000. To convert to pixel coordinates:

const pixelX = (normalizedX / 1000) * imageWidth;
const pixelY = (normalizedY / 1000) * imageHeight;

License

MIT

Available Tools

4 tools

analyze_colorsA

Extract dominant colors from an image region using K-Means clustering in LAB color space. Returns colors sorted by frequency with human-readable names from color.pizza.

ParametersJSON Schema

Name	Required	Description
`image`	Yes	Path to the image file
`bbox`	No	Optional bounding box as [ymin, xmin, ymax, xmax] normalized 0-1000. Defaults to full image.
`top`	No	Number of dominant colors to return (default: 5)

TDQS

A3.5/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden. It discloses the algorithm (K-Means clustering), color space (LAB), and output format (colors sorted by frequency with human-readable names). However, it doesn't mention performance characteristics, error conditions, or limitations like image format support.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is perfectly concise with two sentences that each add value: first explaining the core functionality and method, second describing the output format. No wasted words or redundant information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with no annotations and no output schema, the description provides adequate but minimal context. It explains what the tool does and what it returns, but doesn't address error handling, performance, or integration considerations that would be helpful for an AI agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all parameters thoroughly. The description doesn't add any parameter-specific information beyond what's in the schema, maintaining the baseline score.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific action ('Extract dominant colors'), resource ('from an image region'), and method ('using K-Means clustering in LAB color space'). It distinguishes from potential siblings by specifying color analysis rather than general description or detection.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided about when to use this tool versus alternatives like 'describe' or 'detect'. The description focuses on what the tool does, not when it's appropriate or what problems it solves.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

describeB

Get an AI-generated description of an image. Supports multiple providers (Gemini, OpenAI, Claude).

ParametersJSON Schema

Name	Required	Description
`image`	Yes	Path to the image file
`prompt`	No	Optional question or instruction for the description
`provider`	No	Vision provider to use (default: gemini)
`detail`	No	Level of detail in the description (default: detailed)

TDQS

B3.3/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It mentions support for multiple providers, which adds some context, but lacks details on behavioral traits such as rate limits, authentication needs, error handling, or what the output looks like (e.g., format, length). For a tool with no annotations, this is a significant gap in transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loaded with the core purpose, and efficiently mentions provider support without unnecessary details. Every sentence contributes directly to understanding the tool's functionality, with zero waste or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 4 parameters, no annotations, and no output schema, the description is adequate but incomplete. It covers the basic purpose and provider context, but lacks details on output format, error cases, or integration with sibling tools. For a tool of this complexity, more contextual information would be beneficial to ensure proper usage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all parameters thoroughly. The description adds minimal value beyond the schema by mentioning provider support, but doesn't elaborate on parameter meanings, interactions, or usage examples. Baseline 3 is appropriate as the schema handles most of the parameter documentation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Get an AI-generated description of an image.' It specifies the action (get description) and resource (image), but doesn't explicitly differentiate from sibling tools like 'describe_region' or 'detect' which might have overlapping functionality.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description mentions 'Supports multiple providers (Gemini, OpenAI, Claude),' which implies usage context for provider selection. However, it doesn't provide explicit guidance on when to use this tool versus alternatives like 'describe_region' or 'analyze_colors,' nor does it specify scenarios where this tool is preferred or excluded.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

describe_regionA

Crop an image to a bounding box and describe that region in detail. Use this after detect() to zoom in on specific objects.

ParametersJSON Schema

Name	Required	Description
`image`	Yes	Path to the image file
`bbox`	Yes	Bounding box as [ymin, xmin, ymax, xmax] normalized 0-1000
`prompt`	No	Optional question or instruction for the description
`provider`	No	Vision provider to use (default: gemini)

TDQS

A4.1/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It explains the core functionality (cropping and describing) and mentions a prerequisite relationship with detect(), but doesn't cover important behavioral aspects like error handling, performance characteristics, or what the detailed description output looks like. It provides basic context but lacks comprehensive behavioral transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is perfectly concise with just two sentences that each serve a distinct purpose: the first states what the tool does, the second provides usage guidance. There's zero wasted text, and the information is front-loaded with the core functionality stated immediately.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's moderate complexity (image processing with multiple parameters) and the absence of both annotations and an output schema, the description provides adequate but incomplete context. It explains the purpose and usage relationship well, but doesn't address what the detailed description output contains or provide behavioral details that would be helpful for an AI agent to understand the tool fully.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema description coverage, the input schema already documents all 4 parameters thoroughly. The description doesn't add any parameter-specific information beyond what's in the schema, so it meets the baseline expectation but doesn't provide additional semantic context about how parameters interact or affect the operation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific action ('Crop an image to a bounding box and describe that region in detail') and distinguishes it from sibling tools by explicitly mentioning 'Use this after detect() to zoom in on specific objects.' This provides both the verb+resource combination and sibling differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit guidance on when to use this tool ('Use this after detect() to zoom in on specific objects') and implies alternatives by distinguishing it from the 'describe' sibling tool (which presumably describes entire images rather than cropped regions). This gives clear context for tool selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

detectA

Detect objects in an image and return bounding boxes. Uses Gemini for native bounding box support. Coordinates are normalized 0-1000 as [ymin, xmin, ymax, xmax].

ParametersJSON Schema

Name	Required	Description	Default
`image`	Yes	Path to the image file
`prompt`	No	Optional: what to detect (e.g., 'find all buttons', 'detect UI elements')

TDQS

A4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. It discloses key behavioral traits: it returns bounding boxes, uses Gemini for support, and specifies the coordinate format (normalized 0-1000 as [ymin, xmin, ymax, xmax]). However, it does not cover aspects like rate limits, error handling, or performance characteristics.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core purpose and efficiently adds necessary details in two sentences. Every sentence earns its place by clarifying the tool's function, technology used, and output format without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (object detection with two parameters) and no annotations or output schema, the description is fairly complete. It covers the purpose, technology, and output format, but could benefit from more details on behavioral aspects like error cases or limitations to be fully comprehensive.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents both parameters. The description adds some context by implying the 'prompt' parameter is for specifying what to detect, but it does not provide additional syntax or format details beyond what the schema provides, aligning with the baseline for high coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific action ('detect objects in an image') and the resource ('image'), and it distinguishes from sibling tools like 'analyze_colors' or 'describe' by focusing on object detection with bounding boxes rather than color analysis or general description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for object detection in images, but it does not explicitly state when to use this tool versus alternatives like 'describe' or 'describe_region'. It mentions 'Uses Gemini for native bounding box support', which hints at a specific context, but lacks clear exclusions or named alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

4 tool updatesv1.0.0Jan 2, 2026
- First observedanalyze_colors
- First observeddescribe
- First observeddescribe_region
- First observeddetect

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.8/5.0

Disambiguation5/5

Each tool has a clearly distinct purpose: analyze_colors extracts color information, describe provides general image descriptions, describe_region focuses on specific cropped areas, and detect identifies objects with bounding boxes. The descriptions explicitly differentiate their functions, with no overlap or ambiguity in their intended use cases.

Naming Consistency4/5

The tool names follow a consistent verb-based pattern (analyze, describe, describe, detect) with clear objects (colors, region, detection). The only minor deviation is that describe_region uses an underscore while describe does not, but this is a small inconsistency that doesn't significantly impact readability or predictability.

Tool Count5/5

With 4 tools, this server is well-scoped for its image analysis purpose. Each tool serves a distinct and valuable function in the workflow (detection, description, region-specific analysis, and color extraction), and there are no redundant or unnecessary tools. The count is appropriate for covering core image processing tasks without being overwhelming.

Completeness4/5

The tool set covers the essential image analysis workflow well: detection, general description, region-specific description, and color analysis. A minor gap is the lack of tools for image manipulation (e.g., cropping, resizing) or metadata extraction, but agents can work around this by using describe_region for cropping and the existing tools handle the core AI-driven analysis tasks effectively.

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

mcp A
io.github.pictify-io
Generate images, GIFs, and PDFs from HTML, URLs, or templates — from your AI agent.
Image & Video Processing Multimedia Processing
262
mcp A
online.editclips
Video, audio, and image processing for AI agents: convert, transcribe, upscale - 150+ operations.
Multimedia Processing Audio Processing Image & Video Processing
51
Frenchie A
io.github.Lab94
OCR, transcription, file extraction, and image generation for AI agents via MCP.
AI & Machine Learning Image & Video Processing Speech Processing
72
SnapOG OG Image Generator
com.snapog
Give agents instant OG image generation, social metadata audits, and rendering guidance.
Image & Video Processing Marketing Social Media
2

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/simen/mcp-see'

If you have feedback or need assistance with the MCP directory API, please join our Discord server