Skip to main content
Glama

腾讯 IMA 开放平台(笔记 & 知识库)的 MCP Server。

基于官方 IMA Skill / Agent 接口 移植为独立 MCP Server

凭据

通过环境变量配置:

export IMA_OPENAPI_CLIENTID="your_client_id"
export IMA_OPENAPI_APIKEY="your_api_key"

或写入本地文件:

~/.config/ima/client_id
~/.config/ima/api_key

Related MCP server: Local Knowledge Desk

开发

pnpm install   # 或 npm install
pnpm run build
pnpm run typecheck

MCP 配置示例

{
  "name": "ima",
  "serverType": "local",
  "command": "node",
  "args": ["/path/to/ima-mcp/dist/index.js"],
  "env": {
    "IMA_OPENAPI_CLIENTID": "your_client_id",
    "IMA_OPENAPI_APIKEY": "your_api_key"
  }
}

工具

工具

说明

ima_search_notes

搜索 IMA 笔记,可按标题或正文搜索

ima_list_notes

列出 IMA 笔记。folder_id 为空时列出全部笔记

ima_list_notebooks

列出 IMA 笔记本

ima_get_note_content

获取 IMA 笔记内容。默认返回纯文本

ima_create_note

用 Markdown 内容创建 IMA 笔记

ima_append_note

向已有 IMA 笔记末尾追加 Markdown 内容

ima_insert_images_to_note

向笔记末尾追加 Markdown 并把引用的图片(本地路径、file://、http(s)、data URL)内嵌进笔记;仅 PNG/JPEG/WebP 且严格小于 3MiB,按批追加失败即停

ima_get_image_url

把本地图片上传为 IMA 临时文件,返回临时 download_url

ima_search_knowledge_bases

搜索或列出 IMA 知识库。query 为空时按接口返回默认列表

ima_get_addable_knowledge_bases

获取当前用户可添加内容的 IMA 知识库列表

ima_get_knowledge_base

按知识库 ID 获取 IMA 知识库信息

ima_list_knowledge

浏览 IMA 知识库内容,可传 folder_id 进入文件夹

ima_search_knowledge

在指定 IMA 知识库中搜索内容

ima_import_urls

将网页或微信公众号文章 URL 导入 IMA 知识库。不传 folder_id 时导入根目录

ima_get_media_info

获取知识库媒体的原文访问地址或笔记扩展信息

ima_add_note_to_knowledge

把已有 IMA 笔记关联添加到 IMA 知识库

ima_check_repeated_names

上传文件前检查 IMA 知识库内是否有同名条目

ima_upload_file_to_knowledge

上传本地文件到 IMA 知识库:预检、查重、创建媒体、COS 上传、添加知识。支持 PDF/Word/PPT/Excel/Markdown/图片/TXT/Xmind/HTML/EPUB/音频

ima_raw_call

直接调用 IMA OpenAPI 相对路径,用于未封装的新接口

Available Tools

19 tools
ima_add_note_to_knowledgeC

把已有 IMA 笔记关联添加到 IMA 知识库。

Inputs: title (required), note_id (required), knowledge_base_id (required), folder_id.

ima_append_noteC

向已有 IMA 笔记末尾追加 Markdown 内容。

Inputs: content (required), note_id (required).

ima_check_repeated_namesB

上传文件前检查 IMA 知识库内是否有同名条目。

Inputs: params (required), knowledge_base_id (required), folder_id.

ima_create_noteC

用 Markdown 内容创建 IMA 笔记。

Inputs: content (required), folder_id, folder_name.

ima_get_addable_knowledge_basesC

获取当前用户可添加内容的 IMA 知识库列表。

Inputs: limit, cursor.

ima_get_image_urlA

把本地图片(PNG/JPEG/WebP,严格小于 3MiB)上传为 IMA 临时文件,返回可访问的临时 download_url。

Inputs: image_path (required).

ima_get_knowledge_baseC

按知识库 ID 获取 IMA 知识库信息。

Inputs: ids (required).

ima_get_media_infoC

获取知识库媒体的原文访问地址或笔记扩展信息。

Inputs: media_id (required).

ima_get_note_contentC

获取 IMA 笔记内容。默认返回纯文本。

Inputs: note_id (required), target_content_format.

ima_import_urlsA

将网页或微信公众号文章 URL 导入 IMA 知识库。不传 folder_id 时导入到知识库根目录(接口要求 folder_id 必填,根目录传 knowledge_base_id)。

Inputs: urls (required), knowledge_base_id (required), folder_id.

ima_insert_images_to_noteA

向 IMA 笔记末尾追加 Markdown 内容,并自动把内容里引用的图片(本地路径、file://、http(s) URL 或 data URL)内嵌进笔记。图片仅支持 PNG/JPEG/WebP 且必须严格小于 3MiB;连续文本合并为一批,每张图片单独一批,按原顺序逐批追加,失败即停。dry_run 可预览分批。

Inputs: note_id (required), content, dry_run, file_path.

ima_list_knowledgeC

浏览 IMA 知识库内容,可传 folder_id 进入文件夹。

Inputs: knowledge_base_id (required), limit, cursor, folder_id.

ima_list_notebooksC

列出 IMA 笔记本。

Inputs: limit, cursor, version.

ima_list_notesB

列出 IMA 笔记。folder_id 为空时列出全部笔记。

Inputs: limit, cursor, folder_id, sort_type.

ima_raw_callC

直接调用 IMA OpenAPI 相对路径,用于未封装的新接口。

Inputs: api_path (required), body.

ima_search_knowledgeC

在指定 IMA 知识库中搜索内容。

Inputs: query (required), knowledge_base_id (required), cursor.

ima_search_knowledge_basesC

搜索或列出 IMA 知识库。query 为空时按接口返回默认列表。

Inputs: limit, query, cursor.

ima_search_notesC

搜索 IMA 笔记,可按标题或正文搜索。

Inputs: query (required), end, start, search_type.

ima_upload_file_to_knowledgeB

上传本地文件到 IMA 知识库:预检、查重、创建媒体、COS 上传、添加知识。

Inputs: file_path (required), knowledge_base_id (required), password, folder_id, +3 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    C2.8/5.0

    Scored across 19 tools

    Disambiguation3/5

    Most tools map to distinct resource+action pairs, but two pairs blur: ima_append_note vs ima_insert_images_to_note (which also appends Markdown, just with images) and ima_search_knowledge_bases vs ima_get_addable_knowledge_bases vs ima_get_knowledge_base, which are all 'get knowledge base' variants differentiated mainly by description prose. Similarly ima_list_knowledge vs ima_search_knowledge and ima_check_repeated_names vs ima_upload_file_to_knowledge (upload does precheck+dedupe internally) overlap, so selection requires reading descriptions carefully.

    Naming Consistency4/5

    All 19 tools use a consistent ima_ prefix with snake_case verb_noun structure, which is predictable. Minor deviations exist: some verbs are compound (ima_insert_images_to_note, ima_get_addable_knowledge_bases) and ima_raw_call is not a verb_noun resource action, but overall the convention holds.

    Tool Count3/5

    19 tools is on the heavy side for a notes/knowledge-base integration, and several are thin helpers (ima_check_repeated_names, ima_get_image_url, ima_raw_call) that exist mainly to work around API constraints. Each does earn a place, but the surface is broader than necessary for the core note+KB workflows.

    Completeness3/5

    Read/create/append coverage for notes and KBs is solid, and import/upload/media paths are covered. However obvious lifecycle operations are absent: no update/rename/delete note, no create/delete notebook, and no delete/remove-from-knowledge-base tool, leaving agents at dead ends for maintenance tasks (ima_raw_call is only a workaround).

    Maintenance

    ActivityMaintained
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      An MCP server that enables AI agents to search, read, and create notes across six note-taking platforms (Feishu, Obsidian, Notion, Yuque, OneNote, Evernote) through a single unified interface.
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      A knowledge base MCP server that manages notes with digestion and excretion features, supporting search, read, and stats tools.
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      A learning-oriented MCP server for managing notes, providing tools to create, list, get, update, delete, and search notes, along with resources and prompt templates.
      MIT