ima-mcp-server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 |
|---|---|
| search_knowledge_baseA | 搜索知识库列表。query 传空字符串时返回当前账号下所有可见知识库（含自建与订阅）。知道知识库名称但不知道 ID 时用此接口。 |
| get_knowledge_baseA | 获取知识库详情（描述、推荐问题等）。支持一次查询 1-20 个知识库。 |
| get_knowledge_listA | 浏览知识库内容列表（根目录或指定文件夹），分页返回文件与子文件夹。操作根目录时省略 folder_id。folder_id 以 folder_ 前缀开头。 |
| search_knowledgeA | 在指定知识库中按关键词搜索内容（含文件和文件夹），返回命中的标题、摘要片段。这是知识库内容检索的核心接口。 |
| get_media_infoA | 获取知识库条目的原文内容或下载链接。传入 media_id（来自 get_knowledge_list 或 search_knowledge 的返回）。对微信文章/网页/文件类，返回可访问 URL；对笔记类（media_id 以 note_ 开头），会自动拉取并返回笔记正文（note_content 字段，纯文本）。 |
| get_note_contentA | 读取笔记正文（纯文本）。传入 note_id（笔记的数字 ID，即 get_media_info 返回的 notebook_id，或笔记搜索接口返回的 doc_id）。这是读取 IMA 笔记原文的专用接口。 |
| get_addable_knowledge_base_listA | 获取当前用户有权限添加内容的知识库列表。仅在未指定目标知识库时使用。 |
| import_urlsA | 将网页或微信文章 URL 添加到知识库（1-10 个 URL）。添加到根目录时省略 folder_id。 |
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 8 tools
Tools are mostly distinct: listing knowledge bases, getting details, browsing content, searching, and importing URLs each have clear roles. There is some overlap between get_media_info and get_note_content since both can return note text, but they accept different ID types and are described specifically.
All tool names follow a consistent snake_case verb_noun pattern (get_, search_, import_). The verbs and objects are predictable, and even longer names like get_addable_knowledge_base_list fit the pattern clearly.
With 8 tools, the server is well-scoped for its purpose. Each tool covers a distinct part of the knowledge base workflow without redundancy or bloat.
The server covers listing, searching, retrieving, and importing content, which is a coherent set. Missing create/delete/update operations for knowledge bases or folders, but for a read/import-focused server this is a minor gap rather than a critical failure.