cliproxy
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CLIPROXY_API_KEY | Yes | The API key for authenticating with your CLIProxy service | |
| CLIPROXY_BASE_URL | Yes | The base URL of the CLIProxy API, e.g. http://127.0.0.1:8317/v1 | |
| CLIPROXY_OUTPUT_DIR | No | Directory where generated images will be saved | ./output |
| CLIPROXY_TIMEOUT_MS | No | Timeout for image generation requests in milliseconds | 300000 |
| CLIPROXY_IMAGE_MODEL | No | The image model ID exposed by CLIProxy, e.g. gpt-image-2.5-flare | gpt-image-2.5-flare |
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 |
|---|---|
| list_modelsA | 查询已配置 CLIProxy 的可用模型 ID。列表不保证所有模型支持所有接口。 |
| generate_textA | 通过 CLIProxy 生成文本。支持 Chat Completions 和 Responses；调用可能消耗额度。 |
| generate_imageA | 通过 CLIProxy 的 images/generations 生成一张图片并保存本地，返回绝对路径、实际尺寸和 PNG 预览。默认 gpt-image-2.5-flare，也可指定 gpt-image-2.5-sunburst 或其他模型。可能消耗额度，失败不自动重试。 |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
Each tool has a clearly distinct purpose: listing available models, generating text, and generating images. There is no overlap or ambiguity between them.
All tool names follow a consistent verb_noun snake_case pattern: list_models, generate_text, generate_image. The naming is predictable and easily understood.
Three tools is well-scoped for a narrow proxy service focused on model discovery, text generation, and image generation. Each tool earns its place without unnecessary bloat.
The tool surface covers the core lifecycle of the domain: discovering available models, generating text, and generating images. No obvious critical operations are missing for the stated purpose.