manga-vision-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| VISION_LOG | No | Enable logging (default 1, set to 0 to disable). | 1 |
| NANOGPT_MODEL | No | Legacy model name for the primary slot (used only if PRIMARY_VLM_MODEL is not set). | |
| NSFW_VLM_MODEL | No | Model name for the NSFW VLM slot (inherits primary if not set). | |
| VISION_LOG_DIR | No | Directory for log files (default 'logs/' at repo root). | logs/ |
| NANOGPT_API_KEY | No | Legacy API key for the primary slot (used only if PRIMARY_VLM_API_KEY is not set). | |
| NANOGPT_BASE_URL | No | Legacy base URL for the primary slot (used only if PRIMARY_VLM_BASE_URL is not set). | |
| NSFW_VLM_API_KEY | No | API key for the NSFW VLM slot (inherits primary if not set). | |
| NSFW_VLM_BASE_URL | No | Base URL for the NSFW VLM slot (inherits primary if not set). | |
| PRIMARY_VLM_MODEL | No | Model name for the primary VLM slot (default: z-ai/glm-5.3-flash-uncensored). | z-ai/glm-5.3-flash-uncensored |
| FALLBACK_VLM_MODEL | No | Model name for the fallback VLM slot (active only when all three fallback variables are set). | |
| PRIMARY_VLM_API_KEY | No | API key for the primary VLM slot. | |
| FALLBACK_VLM_API_KEY | No | API key for the fallback VLM slot (active only when all three fallback variables are set). | |
| PRIMARY_VLM_BASE_URL | No | Base URL for the primary VLM slot (default: https://nano-gpt.com/api/v1). | https://nano-gpt.com/api/v1 |
| VISION_MAX_LONG_EDGE | No | Maximum long edge for image resizing (default 1024, 0 = unlimited). | 1024 |
| FALLBACK_VLM_BASE_URL | No | Base URL for the fallback VLM slot (active only when all three fallback variables are set). |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| analyze_imageA | 1枚の画像を解析する（主用途: シナリオから導出された構図・景色・表情の生成仕様への準拠検査）。sourceはローカル絶対パス or HTTP(S) URL（PNG/JPEG/WebP・1枚16MBまで）。promptには生成仕様（promptEn/sceneEnの原文＋subject/direction/台詞）を渡す。modeで検査の型を切り替えられる（既定conformance）。vlmでVLMスロット（primary/nsfw/fallback）を選べる（既定primary）。 |
| compare_imagesB | 2〜9枚の画像を順に Image A, B, C… とラベル付きで送り、比較・照合させる（参照画像×生成候補の突き合わせ・同一仕様での候補比較等）。mode=conformance（既定）は各画像を生成仕様と照合し、refcheck は Image A を正とする参照照合の型を前置する。vlmでVLMスロット（primary/nsfw/fallback）を選べる（既定primary）。 |
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/kjranyone/manga-vision-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server