depu-img-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@depu-img-mcp describe this image: https://example.com/cat.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.
depu-img-mcp
图像理解 MCP 服务器 —— 让不支持图像的文本模型通过 MCP 把图片 + prompt 转发给视觉模型,返回描述文本。自身不做推理,是协议适配与转发层。
特性
MCP v2(
MCPServer+ Streamable HTTP,2026-07-28 规范),同时支持 stdio / SSEDocker 部署(多阶段构建 + docker-compose)
多后端 provider:任意 OpenAI 兼容端点(LiteLLM 网关 / vLLM / OpenAI / DashScope / 智谱 / OpenRouter / Ollama …)
双层 prompt 注入:全局
base_vision_prompt+ per-callprompt+task_type路由(auto/general/ocr/ui/debug/describe)安全:magic byte 校验、大小限制、SSRF 防护、路径白名单
轻量 Web 后台(
/admin):查看配置 + 在线测试图片配置双源:环境变量覆盖
config.toml,密钥支持${ENV}插值
Related MCP server: Vision MCP
快速开始
# 1. 准备 .env(至少填 ADMIN_TOKEN 和视觉后端 API key)
cp .env.example .env
# 编辑 .env 填入 API key
# 2. Docker 启动(首次会自动生成 ./conf/config.toml 默认配置)
docker compose up -d
# 3. 访问后台改配置(或直接编辑 ./conf/config.toml 后重启)
open http://localhost:8080/admin
# MCP 端点:http://localhost:8080/mcp首次启动无需预先准备
config.toml:容器挂载./conf/目录,若里面没有配置文件,会自动从内置模板生成一份。之后可在/admin后台在线编辑,或直接改./conf/config.toml后docker compose restart。
本地运行(开发)
uv sync
uv run python -m depu_img_mcp # 默认 streamable-http
MCP_TRANSPORT=stdio uv run python -m depu_img_mcp # stdio 模式给 Claude Desktop 等MCP 工具
image_understand
image_understand(
image: str, # http(s) URL 或 data:image/...;base64,... URI(内联 base64)。不支持本地文件路径(Docker 部署,容器看不到客户端文件系统)
prompt: str = "", # 用户问题;空则给出通用描述(物体、文字/OCR、布局、颜色等)
) -> strprovider / model 由后台 admin 统一配置,客户端不能指定。这用于企业内网服务,后端路由由运维通过
/admin后台决定。
只有一个工具。客户端传图 + prompt,服务器用后台配置的默认 provider 及其 model 进行视觉理解,返回文本描述。
配置示例
[[providers]]
name = "default"
type = "openai-compat"
base_url = "https://gateway.ai.depu.school/v1"
api_key = "${DEPU_GATEWAY_API_KEY}"
model = "Kimi-K2.7-Code"
auth_header = "bearer"客户端配置(Claude Desktop 示例)
stdio 模式:
{
"mcpServers": {
"depu-img": {
"command": "python",
"args": ["-m", "depu_img_mcp"],
"env": { "MCP_TRANSPORT": "stdio", "DEPU_GATEWAY_API_KEY": "sk-..." }
}
}
}HTTP 模式(支持远程 MCP 的客户端):
{
"mcpServers": {
"depu-img": { "url": "http://localhost:8080/mcp" }
}
}License
MIT
Available Tools
1 toolimage_understandA
Describe or analyze an image using a vision model.
Call this whenever you need to understand an image you cannot see. The backend provider and model are determined by the server admin configuration and cannot be overridden from the client.
Args: image: The image as an http(s) URL, or a data:image/...;base64,... URI (inline base64). Local file paths are NOT supported because the server runs in a container and cannot see the client filesystem — encode the file as a base64 data URI first. prompt: What you want to know about the image. Empty = a general description of the image (objects, text/OCR, layout, colors).
Returns: The vision model's text description of the image.
Inputs: image (required), prompt. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
Only one tool exists, so there is no possibility of confusion or overlapping purposes.
A single tool name is trivially consistent; there are no conflicting naming conventions to assess.
One tool for image understanding is thin but acceptable for a single-purpose server; it sits at the low end of the typical range.
The tool provides comprehensive image understanding (description, OCR, layout, colors) and accepts both URLs and base64, covering the full domain without obvious gaps.
Maintenance
Related MCP Connectors
OCR, transcription, file extraction, and image generation for AI agents via MCP.
Generate images from Claude, ChatGPT, Cursor and Codex with 12 top AI image models. Up to 4 images per call, SVG vectorization, background removal, upscaling and image-to-video. Remote MCP with OAuth, no API keys.
Chat, image, video, and audio models from many vendors behind one remote MCP server and one key.
Generate images from Claude, ChatGPT, Cursor and Codex with 12 top AI image models and 10 tools: up to 4 images per call, SVG vectorization, editing and more. Remote MCP with OAuth, no API keys. Pay per image, no subscription.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables text-only LLMs to analyze images by routing them to an OpenAI-compatible vision backend, supporting local files, URLs, and data URLs.18 npmMIT
- AlicenseAqualityCmaintenanceEnables any MCP client to perform image understanding and OCR via any OpenAI-compatible vision-language model. Supports local, private inference without images leaving the machine.227 npmMIT
- AlicenseNot gradedqualityCmaintenanceProvides vision capabilities to text-only LLMs via MCP, enabling image understanding, Q&A, OCR, and image processing through cloud multimodal APIs.MIT
- AlicenseAqualityDmaintenanceEnables any MCP-capable agent to perform vision tasks like describing images, answering questions, OCR, and comparing images using supported vision backends.5MIT