Agent-Native Calendar
Agent-Native Google Calendar - manage events, sync, and public booking
作者提供的说明(英文原文)
Agentic search over your Dewey document collections from any MCP-compatible client.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
DEWEY_API_KEY, DEWEY_COLLECTION_ID, DEWEY_API_URL标为机密的值是你账户的钥匙。千万不要分享给别人,也不要粘贴到聊天里。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
适用于网页版、桌面版和手机版 Claude:
https://mcp.meetdewey.com/mcp打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"dewey": {
"command": "npx",
"args": [
"-y",
"@meetdewey/mcp"
],
"env": {
"DEWEY_API_KEY": "your-value",
"DEWEY_COLLECTION_ID": "your-value",
"DEWEY_API_URL": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add --transport http dewey https://mcp.meetdewey.com/mcpclaude mcp add dewey --env DEWEY_API_KEY=your-value --env DEWEY_COLLECTION_ID=your-value --env DEWEY_API_URL=your-value -- npx -y @meetdewey/mcp运行前请先填写空着的值。
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"dewey": {
"url": "https://mcp.meetdewey.com/mcp"
}
}
}粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"dewey": {
"command": "npx",
"args": [
"-y",
"@meetdewey/mcp"
],
"env": {
"DEWEY_API_KEY": "your-value",
"DEWEY_COLLECTION_ID": "your-value",
"DEWEY_API_URL": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"dewey": {
"type": "http",
"url": "https://mcp.meetdewey.com/mcp"
}
}
}粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"dewey": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@meetdewey/mcp"
],
"env": {
"DEWEY_API_KEY": "your-value",
"DEWEY_COLLECTION_ID": "your-value",
"DEWEY_API_URL": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
ChatGPT 只能连接互联网上的服务器:
https://mcp.meetdewey.com/mcp菜单名称可能因套餐和版本不同而略有差异。
你的选择通过 Cookie 保存在这台设备上,无需账户。
DEWEY_COLLECTION_ID envDEWEY_API_URL env这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
我们还没有读取这个服务器的工具列表;我们会轮流检查各个端点。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月7日
注册名称已通过域名 meetdewey.com 验证(注册中心会核实域名所有权)
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
尚未检查;我们会轮流检查各个端点
尚未检查;我们会轮流检查各个端点
尚未检查;我们会在检查端点时读取工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
你需要填写:DEWEY_API_KEY
两种方式都可以:安装在你的电脑上,或者连接云端版本。
GitHub 仓库最后更新于–,最新版本(1.5.4)于6个月前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,所以接受远程 MCP 服务器的应用也可以使用,例如开启开发者模式的 ChatGPT。
同一分类中有:Agent-Native Calendar, Excel MCP Server, MCP Server for Excel
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Agent-Native Google Calendar - manage events, sync, and public booking
Create and edit Excel files with AI: charts, PivotTables, formulas. No Excel needed.
Excel automation for AI - Sheets, Power Query, DAX, VBA, Tables, Ranges and more. Windows only.
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
MCP server for Dewey — search and research your document collections from Claude, Cursor, and any MCP-compatible agent. See the full API reference for details.
Add to your claude_desktop_config.json (or equivalent MCP client config):
{
"mcpServers": { "dewey": { "command": "/bin/sh", "args": ["-lc", "npx -y @meetdewey/mcp"], "env": { "DEWEY_API_KEY": "dwy_live_...", "DEWEY_COLLECTION_ID": "..." } } } }
Note for Windows users: replace
"command": "/bin/sh"and"args": ["-lc", "npx -y @meetdewey/mcp"]with"command": "npx"and"args": ["-y", "@meetdewey/mcp"]— the login-shell wrapper is only needed on macOS/Linux to pick up Homebrew and nvm PATH entries that Claude Desktop doesn't inherit.
| Variable | Required | Description |
|---|---|---|
DEWEY_API_KEY | Yes | Your Dewey project API key |
DEWEY_COLLECTION_ID | No | Default collection ID. When set, tools that accept collection_id will fall back to this value. |
DEWEY_API_URL | No | Override the API base URL (default: https://api.meetdewey.com/v1) |
| Tool | Description |
|---|---|
dewey_list_collections | List all collections in the project, including description and research instructions when set |
dewey_search | Hybrid semantic + keyword search over chunk content |
dewey_scan_sections | Lightweight search over section titles and summaries |
dewey_research | Agentic research query with configurable depth — returns a grounded, cited answer |
dewey_get_section | Fetch the full Markdown content of a section by ID |
| Tool | Description |
|---|---|
dewey_list_documents | List documents in a collection with their processing status |
dewey_get_document_sections | List all sections in a document (table of contents with heading levels and IDs) |
dewey_get_document_markdown | Fetch the full converted Markdown content of a document |
dewey_retry_document | Retry a failed document — clears error state and re-queues processing |
dewey_delete_document | Permanently delete a document and all its derived data |
| Tool | Description |
|---|---|
dewey_list_claims | List extracted factual claims from a collection or specific document, filterable by importance (1–5) |
dewey_list_contradictions | List detected contradictions — clusters of conflicting claims with explanations and suggested resolutions |
dewey_detect_contradictions | Trigger an async contradiction detection run across all claims in a collection |
dewey_get_contradiction_run | Get the status and stats of the latest contradiction detection run (use to poll after dewey_detect_contradictions) |
dewey_resolve_contradiction | Apply a resolution instruction to a contradiction or dismiss it |
| Tool | Description |
|---|---|
dewey_detect_duplicates | Trigger an async deduplication run — identifies near-duplicate documents by measuring shared content across chunks and marks one per cluster as canonical |
dewey_get_duplicate_run | Get the status and stats of the latest deduplication run (use to poll after dewey_detect_duplicates) |
dewey_list_duplicate_groups | List near-duplicate groups with canonical + members and coverage percentages |
dewey_promote_duplicate_canonical | Promote a different member to canonical; old canonical becomes near_duplicate |
dewey_disband_duplicate_group | Disband a group; former members rejoin retrieval as distinct documents |
Non-canonical documents are excluded from retrieval and contradiction detection. Requires enableDeduplication: true on the collection (set via dewey_update_collection or the Dewey dashboard).
| Tool | Description |
|---|---|
dewey_get_collection_stats | Get document count, storage, section/chunk/claim counts, and processing status breakdown |
dewey_update_collection | Update collection name, description, research instructions, visibility, and feature flags |
dewey_recompute_summaries | Re-run AI section summarization across all documents (e.g. after changing the LLM model) |
dewey_recompute_captions | Re-run AI captioning for all images and tables across all documents |
dewey_delete_collection | Permanently delete a collection and all its data |
Collections can have natural-language instructions that are automatically injected into the research system prompt — for example, noting units, preferred sources, or how to handle missing information. They can be set in the Dewey dashboard, via the API, or directly through dewey_update_collection. When dewey_resolve_contradiction is used to apply a resolution, the suggested instruction is also appended here automatically.
A typical read-only research workflow:
dewey_list_collections — discover available collections and understand their purposedewey_scan_sections — quickly explore document structure to identify relevant sectionsdewey_get_section — load full content of a specific sectiondewey_search — retrieve the most relevant chunks for a focused questiondewey_research — run a full agentic research query for questions that need multi-step reasoningFor deeper analysis and curation:
dewey_get_collection_stats — assess how much content has been processeddewey_list_claims — surface the most important facts across documentsdewey_list_contradictions — identify where documents disagreedewey_resolve_contradiction — apply or dismiss each contradiction, updating collection instructions automaticallyMIT