CPA Search MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CPA_API_KEY | No | CPA authentication key | |
| HTTPS_PROXY | No | Outbound proxy for live-web fetches (`HTTPS_PROXY`/`HTTP_PROXY`/`ALL_PROXY` are honored) | http://127.0.0.1:7897 |
| CPA_BASE_URL | No | Local CPA proxy address | http://127.0.0.1:8317 |
| CPA_GLM_MODEL | No | Model used by the `glm` engine | glm-5.3-cpa |
| CPA_SEARCH_MODEL | No | Model used by the `gemini` engine | gemini-3.7-flash-high |
| CPA_SEARCH_PROXY | No | Explicit outbound proxy for live-web fetches; set to an empty string to force direct connection |
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 |
|---|---|
| cpa_searchA | 使用本地已登录的 Gemini / Grok / GLM 账号进行实时全网搜索，获取最新技术动态、文档与事实总结，并附带权威来源。 |
| fetch_webpageC | 直接抓取指定 URL 网页的完整正文内容并转换为易读的文本 |
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 2 tools
两个工具功能明确分离：cpa_search用于搜索并返回结果，fetch_webpage用于抓取特定URL的内容。没有重叠或模糊边界，代理可以轻松区分何时使用哪个工具。
两个工具均使用snake_case，且都包含动作词（search, fetch），但cpa_search以名词cpa开头，而fetch_webpage以动词开头，存在轻微不一致。不过整体模式简单且可预测，不影响理解。
仅2个工具对于搜索服务器而言显得单薄，但结合其功能（搜索+网页抓取）已覆盖核心需求。未超出合理范围，但处于评分的下限。
搜索和网页抓取共同构成完成查询-获取详情的基本流程，没有明显缺失的关键操作。但缺少如历史记录、批量处理等扩展功能，仍有小幅度提升空间。