What can you do with this server?

With the mcp-vision-server you can analyze images using various OpenAI-compatible vision models via the analyze_image tool. It provides a unified API to switch between providers (e.g., Zhipu, OpenAI, OpenRouter) without changing client code. Images can be supplied as a URL, local file path, or Base64 string (auto-detected). Configuration settings like provider, base URL, API key, model, temperature, and max tokens are set globally through environment variables or overridden per request. The server integrates with MCP clients such as Claude Code, Codex, Cursor, and Zed.

Which integrations are available for this server?

Provides vision analysis using NVIDIA NIM's vision models, enabling image understanding and visual tasks. Provides vision analysis using OpenAI's vision models, allowing image analysis, text extraction, and visual question answering.

How do I use mcp-vision-server?

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-server what's in this image?" 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.

de en es ko ru zh

mcp-vision-server

by RuyimgByCN

Overview Schema Related Servers Score Discussions

Python

Remote

mcp-vision-server

PyPI Python License MCP

One MCP server for every OpenAI-compatible vision model.

Configure once and use the same analyze_image tool across OpenAI, OpenRouter, Zhipu, Bailian, SiliconFlow and other compatible providers. It works with Claude Code, Codex, Cursor, Zed and any other MCP client.

Why use mcp-vision-server?

✅ Works with any MCP client – Claude Code, Codex, Cursor, Zed and more.
✅ Works with many providers – switch providers without changing prompts or tool calls.
✅ One unified API – one tool (analyze_image) for every OpenAI-compatible vision endpoint.
✅ Flexible image input – URL, local file or Base64 are detected automatically.
✅ Override anywhere – configure globally with environment variables or per request.

Related MCP server: vision-mcp

Quick Start

Install the server.
Set your provider and API key.
Add the MCP server to your client.
Ask:

Describe this screenshot.

If everything is configured correctly, your MCP client will automatically call analyze_image and return the vision model's response.

Features

Single analyze_image tool with a consistent interface.
Supports URL, local file and Base64 image inputs.
Supports 13 built-in provider presets.
Provider selection via VISION_PROVIDER or the provider parameter.
Environment-level and request-level configuration overrides.

Example

Ask your MCP client to analyze an image:

Analyze this screenshot and tell me what UI is shown.

The client calls the MCP tool:

{
  "tool": "analyze_image",
  "arguments": {
    "image": "/path/to/screenshot.png",
    "prompt": "Analyze this screenshot and tell me what UI is shown."
  }
}

The server normalizes the image input, sends it to the selected OpenAI-compatible vision provider, and returns a plain text answer to your MCP client.

Providers

Built-in presets make common OpenAI-compatible vision endpoints easy to use:

Provider	Preset
Zhipu	`zhipu`
Bailian / DashScope	`bailian`
OpenAI	`openai`
SiliconFlow	`siliconflow`
OpenRouter	`openrouter`
Ark / Volcengine	`ark`
StepFun	`stepfun`
Kimi / Moonshot	`kimi`
MiniMax	`minimax`
ModelScope	`modelscope`
NVIDIA NIM	`nvidia`
Novita AI	`novita`

You can also use any other OpenAI-compatible vision endpoint by setting VISION_BASE_URL, VISION_API_KEY, and VISION_MODEL manually.

Install & Run

Requires Python ≥ 3.10 and uv.

cd mcp-vision-server
uv sync                  # install deps
uv run pytest -v         # run tests
uv run ruff check .      # lint
uv run mcp-vision-server # start stdio server

Configuration

Option 1: Provider preset (recommended)

export VISION_PROVIDER=zhipu     # default
export VISION_API_KEY=your_key

See Providers for the full preset list.

You can also use provider-specific env vars (e.g. DASHSCOPE_API_KEY, OPENAI_API_KEY) as fallback.

Option 2: Manual

Variable	Required	Description
`VISION_API_KEY`	Yes	API key
`VISION_BASE_URL`	No	OpenAI-compatible endpoint
`VISION_MODEL`	No	Model name

Tool params (override env per call): image, prompt, image_type, provider, base_url, api_key, model, temperature, max_tokens.

MCP Client Setup

Claude Code (`.mcp.json`)

{
  "mcpServers": {
    "vision": {
      "command": "uv",
      "args": ["run", "--directory", "/path/to/mcp-vision-server", "mcp-vision-server"],
      "env": {
        "VISION_PROVIDER": "zhipu",
        "VISION_API_KEY": "your_key"
      }
    }
  }
}

Claude Code Plugin

# After PyPI publish
claude plugins install RuyimgByCN/mcp-vision-server

# Local test
claude plugins install /path/to/mcp-vision-server

The repo includes a .claude-plugin.json manifest — claude plugins install reads it automatically.

Codex (OpenAI Codex CLI)

Edit ~/.codex/config.toml:

[mcp_servers.vision]
command = "uvx"
args = ["mcp-vision-server"]
env = { VISION_PROVIDER = "zhipu", VISION_API_KEY = "your_key" }

Or for local dev:

[mcp_servers.vision]
command = "uv"
args = ["run", "--directory", "/path/to/mcp-vision-server", "mcp-vision-server"]
env = { VISION_PROVIDER = "zhipu", VISION_API_KEY = "your_key" }

Cursor / other `uvx` clients

Replace command with uvx, args with ["--from", "/path/to/mcp-vision-server", "mcp-vision-server"], same env.

Provider Examples

// Bailian
"env": { "VISION_PROVIDER": "bailian", "VISION_API_KEY": "your_key" }

// OpenAI
"env": { "VISION_PROVIDER": "openai", "VISION_API_KEY": "sk-xxx" }

// Fully custom
"env": {
  "VISION_BASE_URL": "https://your-endpoint/v1",
  "VISION_API_KEY": "your_key",
  "VISION_MODEL": "your-model"
}

Architecture

MCP Client (Claude Code / Codex / Cursor / Zed)
        │
        ▼
mcp-vision-server
        │
        ├── mcp_vision_server/server.py     # MCP tool entrypoints
        ├── mcp_vision_server/config.py     # env/provider/parameter resolution
        ├── mcp_vision_server/image.py      # URL/file/base64 normalization
        └── mcp_vision_server/providers.py  # provider presets
        │
        ▼
OpenAI-compatible Vision API
        │
        ▼
Vision model response

FAQ

Why not call the vision provider directly?

This server gives MCP clients a single, reusable vision tool. You can switch providers without changing client prompts, MCP tool names, or client-side integration code.

Can I use a provider that is not listed?

Yes. Use manual configuration with VISION_BASE_URL, VISION_API_KEY, and VISION_MODEL for any OpenAI-compatible vision endpoint.

Can I override the provider per request?

Yes. Use the provider, base_url, api_key, or model tool parameters to override environment-level configuration for a single call.

What image formats are supported?

The server accepts image URLs, local file paths, and Base64 strings. Input type can be auto-detected or specified with image_type.

Development

uv sync --all-groups
uv run ruff check .
uv run ruff format .
uv run pytest -v
uv build
uv run twine check dist/*

Release checklist

Update the version in pyproject.toml.
Run uv run ruff check ., uv run pytest -v, uv build, and uv run twine check dist/*.
Create and push a version tag, for example v0.1.2.
Let GitHub Actions publish to PyPI through trusted publishing.

Roadmap

Add more provider presets when stable OpenAI-compatible vision endpoints are available.
Add richer examples for Claude Code, Codex, Cursor, and other MCP clients.
Add optional streaming response support if MCP client UX benefits from it.
Split provider-specific behavior into plugins only when providers require custom request logic.

About

Author: RuyimgByCN

License: Personal use only. Commercial use is prohibited — see LICENSE for details. Contact the author for commercial licensing.

中文说明： 个人使用免费，禁止商用。商业授权请联系作者。详见 README_ZH.md。

Available Tools

2 tools

analyze_imageB

Analyze or understand an image.

Use this tool when an MCP client needs image understanding, screenshot analysis, OCR-like text recognition, visual Q&A, or UI restoration.

ParametersJSON Schema

Name	Required	Default
`image`	Yes
`model`	No
`prompt`	No	请详细描述这张图片。
`api_key`	No
`base_url`	No
`provider`	No
`image_type`	No	auto
`max_tokens`	No
`temperature`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

B3.2/5.0

Behavior2/5

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

With no annotations provided, the description carries the full burden for behavioral disclosure. It states the tool can 'analyze' an image but does not reveal that it likely calls an external API (implied by parameters like api_key, base_url, provider), nor does it describe side effects, idempotency, or return behavior beyond the output schema.

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 concise: two sentences summarizing purpose and use cases. It is front-loaded and wastes no words. However, it could be slightly more structured (e.g., separate parameter notes) to improve readability.

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?

Given the tool's complexity (9 parameters, output schema exists, sibling tool), the description is incomplete. It lacks parameter guidance, input/output format details, and prerequisites (e.g., API key requirements). The output schema exists but is not referenced. The description should provide more context for accurate invocation.

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

Parameters1/5

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

Schema description coverage is 0%, yet the description provides no explanation for any of the 9 parameters (image, model, prompt, api_key, base_url, provider, image_type, max_tokens, temperature). It fails to add meaning beyond the schema, leaving the agent to guess parameter usage.

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's purpose: 'Analyze or understand an image.' It provides specific use cases (image understanding, screenshot analysis, OCR, visual Q&A, UI restoration) which distinguishes it from the sibling tool 'list_providers' and gives a precise verb-resource relationship.

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 explicitly lists when to use the tool (e.g., when image understanding or OCR is needed) and implies a specific context. However, it does not mention when not to use it or suggest alternative tools, which would improve guidance.

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

list_providersA

List all supported provider presets as a JSON array.

ParametersJSON Schema

Name	Required	Description	Default
No parameters

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?

No annotations are provided, so the description carries the full burden. It only states output format but omits any behavioral details like performance, rate limits, or data freshness. However, for a simple parameterless list tool, the minimal description is somewhat adequate.

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 a single short sentence that is front-loaded with the key action and resource. Every word earns its place, with no 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 has no parameters and an output schema is present, the description is nearly sufficient. However, it does not elaborate on what 'provider presets' entail, which could be slightly ambiguous. The completeness is high but not perfect.

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?

There are zero parameters, so the description adds no information beyond the empty schema. According to the rubric, 0 params has a baseline score of 4.

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 verb 'List', the resource 'all supported provider presets', and the output format 'as a JSON array'. It effectively distinguishes from the only sibling tool 'analyze_image'.

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?

While no explicit when-to-use or alternatives are given, the context with only one sibling tool 'analyze_image' makes the usage obvious. The description lacks exclusion criteria but remains clear for this simple tool.

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.

2 tool updatesv0.1.1Jul 9, 2026
- First observedanalyze_image
- First observedlist_providers

Install Server

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

TDQS

A3.6/5.0

Disambiguation5/5

The two tools have entirely distinct purposes: analyze_image for image understanding and list_providers for listing provider presets. No overlap or ambiguity.

Naming Consistency5/5

Both tools follow a consistent verb_noun pattern (analyze_image, list_providers), making naming predictable and clear.

Tool Count3/5

Only two tools for a vision server feels slightly thin. While the count is not extreme, it borders on insufficient for typical vision tasks.

Completeness2/5

The server covers only basic image analysis and a provider listing, missing common vision operations like generation, manipulation, or filtering. The tool surface is significantly incomplete.

Maintenance

ActivityMaintained

ResponsivenessNo issues

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
UI Verify A
io.github.igrlk
MCP server for visual regression testing: triage a PR's UI diffs from your coding agent.
9118
anotherai
dev.anotherai
MCP server for building and testing AI agents with multi-model experimentation and insights.
Agent Orchestration Autonomous Agents Testing & QA Tools
2
OpenAI Tools MCP Server B
ai.com.mcp
Focused MCP server for OpenAI image/audio generation (v2.0.0). Wraps endpoints via HAPI CLI.
Image & Video Processing Audio Processing Multimedia Processing
927

Related MCP Servers

z_ai_vision_mcp_server_clone
Image & Video Processing AI & Machine Learning
1orZero
F
license
B
quality
B
maintenance
OpenAI-compatible MCP server for running image analysis tools against your own vision model endpoint.
Updated 2 months ago (2026-06-24 16:06 UTC)
7
16
-
vision-mcp
AI & Machine Learning Image & Video Processing
winton979
A
license
A
quality
B
maintenance
MCP server that provides an analyze_image tool using OpenAI-compatible vision LLMs to describe images from file paths, URLs, or base64 data.
Updated 2 months ago (2026-07-08 07:04 UTC)
1
19
1
MIT
vision-mcp
Image & Video Processing AI & Machine Learning
menoxz
A
license
Not graded
quality
C
maintenance
MCP server for analyzing images using multiple vision LLM providers (OpenCode, OpenAI, Anthropic, Google, and custom OpenAI-compatible endpoints). Provides tools to analyze single or multiple images, list providers, and test vision capabilities.
Updated a month ago (2026-08-01 07:12 UTC)
MIT
mcp-six-eyes
Image & Video Processing AI & Machine Learning
RimunAce
A
license
A
quality
A
maintenance
MCP server that gives text-only AI agents the ability to understand images via vision tools, including multi-image analysis, OCR, comparison, and structured extraction. It uses providers like OpenAI, Anthropic, Gemini, and OpenRouter to return plain text descriptions.
Updated 11 days ago (2026-08-26 16:12 UTC)
4
10
177
MIT

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/RuyimgByCN/mcp-vision-server'

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

mcp-vision-server

Why use mcp-vision-server?

Quick Start

Features

Example

Providers

Install & Run

Configuration

Option 1: Provider preset (recommended)

Option 2: Manual

MCP Client Setup

Claude Code (.mcp.json)

Claude Code Plugin

Codex (OpenAI Codex CLI)

Cursor / other uvx clients

Provider Examples

Architecture

FAQ

Why not call the vision provider directly?

Can I use a provider that is not listed?

Can I override the provider per request?

What image formats are supported?

Development

Release checklist

Roadmap

About

Available Tools

Output Schema

TDQS

Output Schema

TDQS

Tool Schema Changelog

TDQS

Maintenance

Resources

Looking for Admin?

Related MCP Connectors

Related MCP Servers

z_ai_vision_mcp_server_clone

vision-mcp

vision-mcp

mcp-six-eyes

Latest Blog Posts

MCP directory API

Claude Code (`.mcp.json`)

Cursor / other `uvx` clients