Skip to main content
Glama
lbyxunxunnini

mcp-vision

by lbyxunxunnini
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

mcp-vision

GitHub: lbyxunxunnini/mcp-vision · License: MIT · 当前版本：v0.1.0

MCP Server for image recognition, powered by Kimi K2.5 (Infini-AI).

Features

  • recognize_image - Recognize and describe images using multimodal AI

Related MCP server: Image Parse MCP

Prerequisites

Installation

# 1. Extract the archive
tar -xzf mcp-vision.tar.gz
cd mcp-vision

# 2. Install dependencies and build
npm install && npm run build

Claude Code Configuration

Add the following to your Claude Code settings (~/.claude/settings.json or project .claude/settings.json):

{
  "mcpServers": {
    "vision": {
      "command": "node",
      "args": ["/path/to/mcp-vision/dist/index.js"],
      "env": {
        "INFINI_API_KEY": "your-api-key-here"
      }
    }
  }
}

Replace /path/to/mcp-vision with the actual path where you extracted the project.

Usage

Once configured, the mcp__vision__recognize_image tool is available in Claude Code.

Parameters

Parameter

Type

Required

Description

image_path

string

Yes

Absolute path to the local image file

prompt

string

No

Custom instruction, e.g. "extract all text", "describe the UI layout"

Supported Formats

PNG, JPG, JPEG, GIF, WebP, BMP

Example

请识别这张图片: /Users/me/Desktop/screenshot.png

Claude Code will automatically call the MCP tool to process the image.

Environment Variables

Variable

Description

INFINI_API_KEY

Required. Your Infini-AI API key

Available Tools

1 tool
recognize_imageC

Recognize and describe an image using a multimodal model (Kimi K2.5). Returns a text description of the image content.

ParametersJSON Schema
NameRequiredDescriptionDefault
promptNoOptional instruction to guide the recognition, e.g. 'extract all text', 'describe the UI layout', 'what code is shown'
image_pathYesAbsolute path to the local image file

TDQS

C2.9/5.0
Behavior2/5

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

No annotations are provided, so the description must disclose all behavioral traits. It only mentions the model and that it returns text, but lacks details about file format support, size limits, network requirements, or latency.

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

Conciseness4/5

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

The description is very short and to the point. While it is concise, it could benefit from a bit more structure or detail without becoming verbose.

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

Completeness2/5

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

For a tool with no annotations or siblings, and only two parameters, the description is insufficient. It lacks information about return values, error handling, or typical use cases.

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 coverage is 100%. The description adds no extra meaning beyond the schema's parameter descriptions. Baseline score of 3 applies.

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 action (recognize/describe) and the resource (image using a specific model), making the purpose obvious. However, it does not distinguish from potential siblings, but no siblings are listed.

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 on when to use this tool versus alternatives. It does not provide any context about prerequisites, limitations, or when it should not be used.

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.

  1. 1 tool updatev1.0.0
    • First observedrecognize_image
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

B3.1/5.0

Scored across 1 tool

Disambiguation5/5

With only one tool, there is no possibility of ambiguity or overlap with other tools. The tool's purpose is clearly defined.

Naming Consistency5/5

The single tool uses a clear verb_noun pattern (recognize_image) with snake_case, which is consistent and readable. No inconsistency exists.

Tool Count2/5

A single tool is too few for a server named 'mcp-vision,' which implies a broader scope. The tool count falls into the 'too few' category, limiting functionality.

Completeness2/5

The server only offers image description, lacking other common vision tasks (e.g., object detection, OCR). This is a significant gap for a general vision server.

Maintenance

ActivityStale
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers