Which integrations are available for this server?

Allows performing precise OCR with structured results (including coordinates and confidence) using Baidu's OCR service. Allows performing image analysis and OCR using OpenAI's vision models (e.g., GPT-4o) via their API.

How do I use mcp-vision?

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-vision describe this image: ./screenshot.png" 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-vision

by hahahahanb

Overview Schema Related Servers Score Discussions

Python

Remote

MCP-VISION

为 Claude Code、Codex CLI、OpenCode 等 AI 编程工具补齐图像识别能力的 MCP Server。

解决什么问题

Claude Code 配合 DeepSeek 等纯文本模型使用时，无法理解图片内容——截图里的报错、UI 设计稿、手绘架构图、文档扫描件，模型统统"看不见"。

mcp-vision 作为 MCP Server 插件运行，自动调用多模态视觉 API 完成图像分析，将结果以文本形式返回给 AI 编程工具，让 DeepSeek 等"看图说话"。

┌─────────────┐     图片路径/URL      ┌─────────────┐    多模态 API     ┌──────────────┐
│  AI 编程工具  │ ──────────────────→  │ mcp-vision  │ ──────────────→  │  视觉模型 API  │
│ Claude Code  │                      │  MCP Server  │                  │ 硅基流动/阿里.. │
│  Codex CLI   │ ←──────────────────  │             │ ←──────────────  │              │
│   OpenCode   │     文字分析结果      │             │     图片分析结果   │              │
└─────────────┘                      └─────────────┘                  └──────────────┘

Related MCP server: vision-mcp

工具说明

工具	用途	底层
`analyze_image`	图片内容分析（描述、问答、图表解读）	多模态 LLM
`ocr_extract`	从图片/PDF 提取文字（自然语言返回）	多模态 LLM
`ocr_precise`	精准 OCR（结构化结果，含坐标和置信度）	传统 OCR 引擎

所有工具均支持本地文件路径和远程 URL。

快速开始

安装

pip install mcp-vision

或使用 uv：

uv pip install mcp-vision

最简配置

只需一个 API Key 即可运行。推荐使用硅基流动（SiliconFlow），注册即送免费额度：

# 注册地址：https://cloud.siliconflow.cn
SILICONFLOW_API_KEY=sk-your-key

配置 AI 编程工具

Claude Code

~/.claude/settings.json：

{
  "mcpServers": {
    "mcp-vision": {
      "command": "uvx",
      "args": ["mcp-vision"],
      "env": {
        "SILICONFLOW_API_KEY": "sk-your-key"
      }
    }
  }
}

Codex CLI

~/.codex/config.toml：

[mcp_servers.mcp-vision]
command = "uvx"
args = ["mcp-ocr"]

[mcp_servers.mcp-vision.env]
SILICONFLOW_API_KEY = "sk-your-key"

Cursor

.cursor/mcp.json：

{
  "mcpServers": {
    "mcp-vision": {
      "command": "uvx",
      "args": ["mcp-vision"],
      "env": {
        "SILICONFLOW_API_KEY": "sk-your-key"
      }
    }
  }
}

OpenCode

opencode.json：

{
  "mcp": {
    "mcp-vision": {
      "type": "local",
      "command": ["uvx", "mcp-vision"],
      "environment": {
        "SILICONFLOW_API_KEY": "sk-your-key"
      }
    }
  }
}

支持的 Provider

通过 MCP_OCR_PROVIDER 环境变量切换，默认 siliconflow。

多模态 LLM（图片分析 / OCR 提取）

Provider	值	API Key 环境变量	默认模型
硅基流动（默认）	`siliconflow`	`SILICONFLOW_API_KEY`	DeepSeek-OCR
阿里百炼	`dashscope`	`DASHSCOPE_API_KEY`	qwen-vl-max
火山引擎	`volcengine`	`VOLCENGINE_API_KEY`	doubao-1.5-vision-pro-32k
OpenAI	`openai`	`OPENAI_API_KEY`	gpt-4o
Anthropic	`anthropic`	`ANTHROPIC_API_KEY`	claude-sonnet-4-6
自定义 API	`custom`	`MCP_OCR_API_KEY`	需手动指定

硅基流动以外的 Provider 需额外设置对应的模型环境变量（如 DASHSCOPE_MODEL、OPENAI_MODEL）。

切换视觉模型

每个 Provider 都有内置默认模型，通过对应的 *_MODEL 环境变量可以覆盖：

Provider	模型环境变量	默认值
硅基流动	`SILICONFLOW_MODEL`	`deepseek-ai/DeepSeek-OCR`
阿里百炼	`DASHSCOPE_MODEL`	`qwen-vl-max`
火山引擎	`VOLCENGINE_MODEL`	`doubao-1.5-vision-pro-32k`
OpenAI	`OPENAI_MODEL`	`gpt-4o`
Anthropic	`ANTHROPIC_MODEL`	`claude-sonnet-4-6`

以硅基流动为例，在 .env 或环境变量中指定：

MCP_OCR_PROVIDER=siliconflow
SILICONFLOW_API_KEY=sk-your-key
SILICONFLOW_MODEL=deepseek-ai/DeepSeek-OCR

在 AI 编程工具的 env 配置中直接指定：

{
  "mcpServers": {
    "mcp-vision": {
      "command": "uvx",
      "args": ["mcp-vision"],
      "env": {
        "SILICONFLOW_API_KEY": "sk-your-key",
        "SILICONFLOW_MODEL": "Qwen/Qwen2.5-VL-72B-Instruct"
      }
    }
  }
}

提示：请确保指定的模型是视觉模型（支持图片输入）。纯文本模型会导致 API 调用失败。

传统 OCR（精准提取，结构化结果）

Provider	值	环境变量
百度 OCR	`baidu_ocr`	`BAIDU_OCR_API_KEY` + `BAIDU_OCR_SECRET_KEY`
腾讯云 OCR	`tencent_ocr`	`TENCENT_SECRET_ID` + `TENCENT_SECRET_KEY`

传统 OCR 仅支持 ocr_precise 工具，返回结构化数据（含文字坐标和置信度）。

自定义 Provider

兼容所有 OpenAI /chat/completions 协议的视觉 API：

MCP_OCR_PROVIDER=custom
MCP_OCR_API_KEY=your-key
MCP_OCR_BASE_URL=https://your-api.com/v1
MCP_OCR_MODEL=your-vision-model

环境变量完整列表

# Provider 选择（默认 siliconflow）
MCP_OCR_PROVIDER=siliconflow

# === 硅基流动 ===
SILICONFLOW_API_KEY=your-key
# SILICONFLOW_MODEL=deepseek-ai/DeepSeek-OCR    # 可选，覆盖默认模型

# === 阿里百炼 ===
# DASHSCOPE_API_KEY=your-key
# DASHSCOPE_MODEL=qwen-vl-max

# === 火山引擎 ===
# VOLCENGINE_API_KEY=your-key
# VOLCENGINE_MODEL=doubao-1.5-vision-pro-32k

# === OpenAI ===
# OPENAI_API_KEY=sk-your-key
# OPENAI_MODEL=gpt-4o

# === Anthropic ===
# ANTHROPIC_API_KEY=sk-ant-your-key
# ANTHROPIC_MODEL=claude-sonnet-4-6

# === 百度 OCR ===
# BAIDU_OCR_API_KEY=your-api-key
# BAIDU_OCR_SECRET_KEY=your-secret-key

# === 腾讯云 OCR ===
# TENCENT_SECRET_ID=your-secret-id
# TENCENT_SECRET_KEY=your-secret-key

# === 自定义 OpenAI 兼容 API ===
# MCP_OCR_API_KEY=your-key
# MCP_OCR_BASE_URL=https://your-api.com/v1
# MCP_OCR_MODEL=your-model

也可将这些变量写在项目根目录的 .env 文件中，Server 启动时自动加载。

图片格式

PNG、JPG、JPEG、GIF、BMP、WebP、PDF

自动触发：粘贴图片即分析

在 Claude Code 中可以通过 Skill 实现粘贴图片后自动调用 mcp-vision，无需手动输入命令。

步骤一：创建 Skill 文件

在项目根目录创建 .claude/skills/image-analysis.md：

---
name: image-analysis
description: 当用户粘贴图片时自动调用 mcp-vision 进行分析
trigger: 当用户消息中包含图片（[Image: ...] 或 [Image #N] 标记）时自动触发
---

当用户消息中包含图片标记时，自动调用 mcp-vision 的工具处理：

1. **如果用户没有文字说明**，默认调用 `analyze_image` 工具分析图片内容
2. **如果用户附带了文字说明**，将文字说明作为 prompt 传给对应工具

根据用户意图选择工具：
- 图片描述、问答、图表分析 → `analyze_image`
- 提取文字 → `ocr_extract`
- 需要坐标和置信度 → `ocr_precise`

图片路径直接从图片标记中提取，作为 image 参数传入。

步骤二：在 CLAUDE.md 中注册触发规则

在项目的 CLAUDE.md（或全局 ~/.claude/CLAUDE.md）中添加：

### 图片自动分析
- **触发条件**：当用户消息中包含 `[Image:`、`[Image #N]` 标记时（即通过 Alt+V 粘贴的图片）
- **执行动作**：立即调用 `image-analysis` skill，根据图片内容和用户意图自动选择分析模式
- **无需用户明确指示**：只要消息中有图片就应触发，无文字说明时自动智能路由

效果

配置完成后：

Alt+V 粘贴图片 → Claude Code 自动调用 mcp-vision 的 analyze_image → 返回图片分析结果
粘贴图片 + 文字说明（如"提取这里的文字"） → 自动路由到 ocr_extract
无需手动输入任何命令

本地开发

# 克隆仓库
git clone https://github.com/hahahahanb/mcp-vision.git
cd mcp-vision

# 安装依赖
uv sync

# 运行测试
uv run pytest -v

# MCP Inspector 调试
uv run mcp dev src/mcp_ocr/server.py

本地安装后，AI 编程工具的配置可改为直接运行源码：

{
  "mcpServers": {
    "mcp-vision": {
      "command": "uv",
      "args": ["run", "mcp-vision"],
      "env": {
        "SILICONFLOW_API_KEY": "sk-your-key"
      }
    }
  }
}

License

MIT

Available Tools

3 tools

analyze_imageA

分析图片内容。支持本地文件路径和远程 URL。可用于图像描述、视觉问答、图表分析等场景。

Args: image: 图片路径（本地绝对路径）或远程 URL prompt: 分析提示词，描述你希望如何分析这张图片。默认详细描述图片内容

ParametersJSON Schema

Name	Required	Description	Default
`image`	Yes
`prompt`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A3.8/5.0

Behavior2/5

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

No annotations are provided, so the description must bear full burden. It states that the tool analyzes images and supports local paths and URLs, but does not disclose non-destructive behavior, authentication needs, or rate limits. It implies read-only operation but is not explicit.

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 concise: a single-sentence overview followed by a clear Args list. No unnecessary words, though the structure could be improved with a more formal separation of purpose and usage.

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?

The description covers the tool's purpose, input parameters, and use cases. However, it lacks details on supported image formats, size limits, or performance considerations. The presence of an output schema mitigates the need for return value explanation.

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

Parameters4/5

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

Schema has 0% description coverage, so the description must compensate. It explains the 'image' parameter as a local path or URL, and 'prompt' as an analysis prompt with default behavior. This adds significant meaning beyond the bare schema types.

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 tool analyzes image content and mentions specific use cases (image description, visual QA, chart analysis). It implicitly distinguishes from siblings ocr_extract and ocr_precise, which are OCR tools, so the purpose is well-defined.

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

Usage Guidelines4/5

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

The description lists scenarios where the tool is applicable ('可用于图像描述、视觉问答、图表分析等场景'), providing clear context. However, it lacks explicit when-not-to-use guidance or direct mention of alternatives, though the sibling tools imply different use cases.

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

ocr_extractA

从图片或 PDF 中提取文字（OCR）。适合识别截图、文档、代码中的文本内容。

Args: image: 图片或 PDF 文件路径（本地绝对路径）或远程 URL prompt: OCR 提示词。默认提取并格式化所有文字内容

ParametersJSON Schema

Name	Required	Description	Default
`image`	Yes
`prompt`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A3.7/5.0

Behavior2/5

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

No annotations are provided, so the description must fully disclose behavioral traits. However, it does not mention performance, limitations (e.g., file size, language support), or side effects. Only basic functionality is stated.

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 concise, with a clear front-loaded sentence explaining purpose, followed by parameter descriptions. Every sentence adds value without 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 the tool's simplicity and the presence of an output schema, the description covers core aspects. However, it lacks details on input constraints (e.g., file size limits, supported languages) and error conditions, leaving some gaps.

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

Parameters4/5

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

Schema coverage is 0%, but the description explains both parameters: image as local path or URL, prompt as OCR hint with default behavior. This adds meaning beyond the schema, though more detail (e.g., supported image formats) could be beneficial.

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 tool extracts text from images or PDFs (OCR), and provides use cases like screenshots, documents, and code. This makes the purpose unambiguous and distinct from siblings like analyze_image and ocr_precise.

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 use cases ('suitable for recognizing screenshots, documents, code text'), but does not explicitly state when to use this tool versus alternatives like ocr_precise. There is no mention of when not to use it.

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

ocr_preciseA

使用传统 OCR 引擎精准提取图片中的文字（返回结构化结果，含文字坐标和置信度）。需要配置百度 OCR 或腾讯云 OCR 作为 Provider。适合需要精确文字位置信息的场景（如发票、卡证、表格）。

Args: image: 图片文件路径（本地绝对路径）或远程 URL

ParametersJSON Schema

Name	Required	Description	Default
`image`	Yes

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A4.2/5.0

Behavior3/5

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

无注释信息，描述承担了全部告知责任。提到使用传统OCR引擎、需配置Provider、返回结构化结果，但未提及是否具有破坏性、速率限制或其他约束。对于无注释工具来说，信息基本充分，但未完整披露所有行为。

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?

描述精炼，首句明确核心功能，随后提供配置要求和适用场景，最后以Args列表说明参数。无冗余信息，结构清晰，信息密度高。

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?

考虑到有输出schema，描述不必要解释返回值，但已提及返回结构和内容。单参数工具，描述覆盖了关键使用前提和场景。但缺少对图片格式、大小限制等边缘情况的说明，整体上足够完整。

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

Parameters4/5

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

单个参数image，描述补充了其含义为本地绝对路径或远程URL，这在schema中未提供。参数说明清晰，弥补了schema描述覆盖率0%的不足，但未进一步说明支持的图片格式或最大尺寸。

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?

明确说明功能：使用传统OCR引擎精准提取图片文字，返回结构化结果包括坐标和置信度。同时通过场景描述（发票、卡证、表格）与兄弟工具区分，使用户清楚适用场景。

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

Usage Guidelines4/5

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

指出需要配置百度或腾讯云OCR作为Provider，并说明适合需要精确文字位置信息的场景。但未明确说明何时不应使用此工具，也未直接提及兄弟工具作为替代方案，略显不足。

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.

3 tool updatesv1.0.0Jul 12, 2026
- First observedanalyze_image
- First observedocr_extract
- First observedocr_precise

Install Server

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

TDQS

A3.8/5.0

Disambiguation4/5

Most tools are distinct: analyze_image handles general analysis, while ocr_extract and ocr_precise both do OCR but differ in precision and output structure. However, an agent might confuse ocr_extract with ocr_precise since both extract text.

Naming Consistency4/5

Two tools follow an 'ocr_' prefix pattern, while analyze_image uses a different verb_noun structure. The naming is mostly consistent within subgroups but lacks a unified pattern across all tools.

Tool Count4/5

3 tools is slightly thin for a 'vision' server, but covers core analysis and OCR functions. The count is appropriate for a focused utility, though more tools could be beneficial.

Completeness3/5

Basic image analysis and OCR are covered, but missing common vision tasks like object detection or image manipulation. The toolset feels minimal for general vision needs, leaving notable gaps.

Maintenance

ActivityInactive

ResponsivenessSyncing

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

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
mcp-qwen-imageOAuth
io.github.AceDataCloud
MCP server for Qwen Image 3 AI image generation
AI & Machine Learning Image & Video Processing
1
Danushkumar-V-mcp-discordOAuth
ai.smithery
An MCP server that integrates with Discord to provide AI-powered features.
Communication Social Media App Automation
2
Writingmate MCPOAuth
ai.writingmate
Use AI models for chat, image, and video generation from Claude Code and other MCP hosts.
AI & Machine Learning Image & Video Processing
1

Related MCP Servers

omni-vision-pro
Image & Video Processing Code Analysis AI & Machine Learning
0xnurrabby
A
license
A
quality
B
maintenance
MCP server that analyzes images, reads code and ZIP archives, and provides text context for non-vision models.
Updated a month ago (2026-08-05 05:45 UTC)
3
17
2
MIT
vision-mcp
Image & Video Processing AI & Machine Learning
sulghu
A
license
Not graded
quality
B
maintenance
An MCP server for image recognition and OCR via OpenAI-compatible vision APIs, supporting local files, URLs, and data URLs. Enables natural language image description and text extraction.
Updated a month ago (2026-08-05 19:52 UTC)
21
2
MIT
vision-mcp
Image & Video Processing AI & Machine Learning
Peter-Lpt
F
license
Not graded
quality
B
maintenance
A lightweight MCP server that provides vision capabilities to text-only models like Claude Code and Codex by forwarding images to an OpenAI-compatible multimodal model, offering tools for image analysis and OCR.
Updated 19 days ago (2026-08-19 06:22 UTC)
-
Luma Vision MCP
Image & Video Processing AI & Machine Learning
harryopo
F
license
A
quality
C
maintenance
An MCP server that adds visual understanding to text-only LLMs via image understanding, OCR, and image comparison tools, with multi-provider fallback and context-aware Focus Hint for precise descriptions.
Updated a month ago (2026-08-08 08:19 UTC)
3
-

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/hahahahanb/mcp-vision'

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