opencode-eyes
Click on "Install 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., "@opencode-eyesDescribe this image for me."
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.
opencode-eyes 👁️
MCP server that provides image description capability using StepFun Step-3.7-flash multimodal model.
为不具备多模态能力的模型提供**"眼睛"**。将图片输入,即可获得详细的图片文字描述。
功能
工具 | 说明 |
| 描述一张图片的内容,使用 StepFun Step-3.7-flash 多模态大模型 |
Related MCP server: glm4v-vision-mcp
环境变量
变量 | 必填 | 默认值 | 说明 |
| 是 | — | StepFun API Key |
| 否 |
| 使用的模型名称(Step Plan 专用地址 |
| 否 |
| StepFun API 请求超时(秒) |
| 否 |
| 发送前图片最长边缩放到该像素,0 表示不缩放 |
| 否 |
| 发送前 JPEG 压缩质量(0-100) |
更新日志 (v1.0.2)
修复 MCP -32001 Request timed out:发送前将图片缩放/压缩为 JPEG,大幅减小 payload、降低 API 延迟,避免超过 MCP 客户端默认 5s 超时。
修复空描述:
step-3.7-flash有时把答案放在reasoning_content/reasoning而content为空,现已自动回退。修复 Windows 中文乱码:stdout/stdin 改为 UTF-8 字节读写。
新增
ping方法支持,更健壮的 MCP 握手。
注意:opencode 的 MCP 请求超时默认为 5000ms。若仍需更宽松的超时,可在 opencode 配置中为该 MCP 设置
"timeout": 120000,或全局设置"experimental": { "mcp_timeout": 120000 }。
安装
pip install Pillow运行
# 设置环境变量
set STEP_API_KEY=你的StepFun API Key
# 启动服务
python -m opencode_eyes在 OpenCode 中配置
{
"mcp": {
"opencode-eyes": {
"type": "local",
"command": ["python", "-m", "opencode_eyes"],
"enabled": true,
"timeout": 120000,
"environment": {
"STEP_API_KEY": "你的StepFun API Key"
}
}
}
}License
MIT
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseAqualityBmaintenanceMCP server for image recognition, supporting multiple vision backends (Anthropic, Zhipu, Ollama) to describe, answer questions, and analyze images.3461MIT
- AlicenseBqualityCmaintenanceMCP server that provides image analysis, OCR text extraction, and image description using the GLM-4V Flash model from Zhipu AI.36MIT
- Alicense-qualityBmaintenanceMCP server that gives text-only LLMs vision capabilities by using a free multimodal model to perceive images, audio, and video, returning text for the main model to reason with.2,1921MIT
- Alicense-qualityCmaintenanceEnables text-only models to understand images through a conversational MCP server, supporting multi-turn follow-ups, URL inputs, and OpenAI-compatible vision APIs.1MIT
Related MCP Connectors
MCP server for MiniMax H3 multimodal video generation
MCP server for Wan AI video generation
MCP server for Grok Imagine AI video generation
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/bauerelizabeth07139/opencode-eyes'
If you have feedback or need assistance with the MCP directory API, please join our Discord server