multi-judge-consensus
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MJC_GLM_KEY | No | API key for Zhipu GLM provider. | |
| MJC_KIMI_KEY | No | API key for Kimi provider. | |
| MJC_QWEN_KEY | No | API key for Alibaba Qwen provider. | |
| MJC_DOUBAO_KEY | No | API key for Doubao provider. | |
| MJC_DEEPSEEK_KEY | No | API key for DeepSeek provider. | |
| MJC_DASHSCOPE_KEY | No | API key for DashScope provider. |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| reviewA | 多模型共识审查：对 Agent 输出做幻觉/事实/逻辑错误交叉审查（验证器零成本先行，初筛+委员会+辩论）。返回裁决 verdict(pass/revise/reject/need_human) 与逐条问题 issues。 |
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 1 tool
只有一个工具，不存在与其他工具混淆或选择冲突的情况。
工具名为简洁的动词 review，没有混合命名风格或一致性问题。
单个工具能完成核心审查任务，但作为多模型共识服务略显单薄，属于 1-2 个工具的边界情况。
review 工具覆盖了核心的共识审查、裁决和问题输出，没有明显死胡同；但缺少配置、历史记录等辅助能力。