ima-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@ima-mcp search my notes about AI"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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_keyRelated MCP server: Local Knowledge Desk
开发
pnpm install # 或 npm install
pnpm run build
pnpm run typecheckMCP 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 |
| 搜索 IMA 笔记,可按标题或正文搜索 |
| 列出 IMA 笔记。folder_id 为空时列出全部笔记 |
| 列出 IMA 笔记本 |
| 获取 IMA 笔记内容。默认返回纯文本 |
| 用 Markdown 内容创建 IMA 笔记 |
| 向已有 IMA 笔记末尾追加 Markdown 内容 |
| 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 |
| 把本地图片上传为 IMA 临时文件,返回临时 download_url |
| 搜索或列出 IMA 知识库。query 为空时按接口返回默认列表 |
| 获取当前用户可添加内容的 IMA 知识库列表 |
| 按知识库 ID 获取 IMA 知识库信息 |
| 浏览 IMA 知识库内容,可传 folder_id 进入文件夹 |
| 在指定 IMA 知识库中搜索内容 |
| 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 |
| 获取知识库媒体的原文访问地址或笔记扩展信息 |
| 把已有 IMA 笔记关联添加到 IMA 知识库 |
| 上传文件前检查 IMA 知识库内是否有同名条目 |
| 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 |
| 直接调用 IMA OpenAPI 相对路径,用于未封装的新接口 |
Available Tools
19 toolsima_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
Scored across 19 tools
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.
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.
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.
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
Related MCP Connectors
An MCP server that used to create notes
KnowMan MCP server: search, ask, save and read your Knowledge Base from any MCP client.
Search and manage your team's knowledge from MCP clients.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceAn 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
- FlicenseAqualityBmaintenanceA local MCP server for managing Markdown notes, enabling create, list, read, search, summarize, and delete operations through natural language.61-
- AlicenseNot gradedqualityDmaintenanceA knowledge base MCP server that manages notes with digestion and excretion features, supporting search, read, and stats tools.MIT
- AlicenseNot gradedqualityDmaintenanceA 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