Vision Bridge MCP Server
by Hopcos
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_HOST | No | HTTP 监听地址，默认 127.0.0.1 | 127.0.0.1 |
| MCP_PORT | No | HTTP 监听端口，默认 8081 | 8081 |
| MCP_AUTH_MODE | No | HTTP 认证模式：none 或 token，默认 none | none |
| MCP_LOG_LEVEL | No | 日志级别：DEBUG/INFO/WARNING/ERROR，默认 INFO | INFO |
| MCP_TRANSPORT | No | 传输模式：stdio 或 http，默认 stdio | stdio |
| VISION_API_KEY | No | 本地模型 API 密钥，默认 any | any |
| VISION_BACKEND | No | 视觉后端：third_party / local_api / paddleocr / tesseract / custom_api / auto，默认third_party | third_party |
| VISION_TIMEOUT | No | 请求超时（秒），默认 60 | 60 |
| VISION_API_BASE | No | 本地多模态模型 API 地址（local_api 后端必填） | |
| VISION_OCR_LANG | No | PaddleOCR 语言，默认 ch | ch |
| MCP_SERVER_TOKEN | No | HTTP 客户端认证 Token（MCP_AUTH_MODE=token 时必填） | |
| VISION_MAX_TOKENS | No | 最大生成 token 数，默认 4096 | 4096 |
| VISION_MODEL_NAME | No | 本地模型名称（local_api 后端必填） | |
| VISION_OCR_USE_GPU | No | PaddleOCR 是否使用 GPU，默认 false | false |
| VISION_TESSERACT_CMD | No | Tesseract 可执行文件路径，默认 tesseract | tesseract |
| VISION_CUSTOM_API_URL | No | 自定义 API URL（custom_api 后端必填） | |
| VISION_MAX_CONCURRENT | No | 最大并发处理数，默认 3 | 3 |
| VISION_MAX_IMAGE_SIZE | No | 原始图片最大字节数，默认 20971520 | 20971520 |
| VISION_TESSERACT_LANG | No | Tesseract 语言包，默认 chi_sim+eng | chi_sim+eng |
| VISION_CUSTOM_API_METHOD | No | 自定义 API 请求方法，默认 POST | POST |
| VISION_CUSTOM_API_TIMEOUT | No | 自定义 API 超时（秒），默认 30 | 30 |
| VISION_THIRD_PARTY_API_KEY | No | 第三方 API Key（third_party 后端必填） | |
| VISION_THIRD_PARTY_API_BASE | No | 第三方云端视觉 API Base URL（third_party 后端必填） | |
| VISION_THIRD_PARTY_MODEL_NAME | No | 第三方视觉模型名称（third_party 后端必填） |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
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/Hopcos/vision-bridge-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server