GLM-4.6V-Flash MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GLM_MODEL | No | 覆盖模型 ID (override the model ID) | glm-4.6v-flash |
| GLM_API_KEY | No | Alternative environment variable for the Zhipu API Key (compatible with ZHIPU_API_KEY) | |
| GLM_TIMEOUT | No | 请求超时秒数 (request timeout in seconds) | 120 |
| GLM_API_BASE | No | 覆盖接口地址 (override the API base URL) | https://open.bigmodel.cn/api/paas/v4/chat/completions |
| ZHIPU_API_KEY | No | 智谱 API Key（必填，兼容 GLM_API_KEY） |
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| analyze_imageA | 使用 GLM-4.6V-Flash 分析一张图片（OCR、内容理解、表格解析、缺陷检测等）。 Args: image: 图片地址，支持 http(s) URL、data URI，或本地图片文件路径。 prompt: 对图片提出的问题或指令。 thinking: 是否开启深度思考模式。 temperature: 采样温度，0~1。 max_tokens: 最大输出 token 数。 |
| analyze_videoA | 使用 GLM-4.6V-Flash 分析一段视频（视频需为可访问的 URL 或本地视频文件）。 Args: video: 视频地址，支持 http(s) URL、data URI，或本地视频文件路径。 prompt: 对视频提出的问题或指令。 thinking: 是否开启深度思考模式。 temperature: 采样温度，0~1。 max_tokens: 最大输出 token 数。 |
| analyze_fileA | 使用 GLM-4.6V-Flash 分析文档/文件（PDF、TXT 等，支持 URL、data URI 或本地路径）。 Args: file: 文件地址，支持 http(s) URL、data URI，或本地文件路径。 prompt: 对文件提出的问题或指令。 thinking: 是否开启深度思考模式。 temperature: 采样温度，0~1。 max_tokens: 最大输出 token 数。 |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| help_resource | 读取 GLM MCP 资源的使用方法、payload JSON 格式与可直接使用的示例 URI。 |
TDQS
Scored across 3 tools
Each tool targets a distinct input type (image, video, file), making their purposes clearly separable. There is no overlap in functionality; the only difference is the media format being analyzed.
All tool names follow the exact same verb_noun pattern: analyze_ + media type. This is perfectly consistent and predictable.
Three tools is an appropriate scope for a multimodal analysis server, covering the primary input types without unnecessary bloat.
The toolset covers image, video, and document analysis, which are the most common inputs. Audio analysis is missing, but this is a minor gap given the focus on visual/file understanding.