Agent-Native Calendar
Agent-Native Google Calendar - manage events, sync, and public booking
作者による説明(英語の原文)
Your notes in one folder on your own server; AI clients read and edit it under write policies
この3つを1つのスコアにまとめることはしません。意見、測定、人気はそれぞれ別のものだからです。
このサーバーのやさしい解説はまだ書いていません。以下はレジストリから読み取った事実です。
使っているAIアプリを選んで、設定をコピーしてください。
EVERKEEP_VAULT, EVERKEEP_CONFIG必要なもの
どのアプリを使っていますか?
上でアプリを選んでください。選んだアプリを覚えておくので、次からはボタンに「…にインストール」と表示されます。
Claude Desktop → Settings → Developer → Edit Config を開き、claude_desktop_config.json にこれを貼り付けます
{
"mcpServers": {
"everkeep": {
"command": "npx",
"args": [
"-y",
"everkeep"
],
"env": {
"EVERKEEP_VAULT": "your-value",
"EVERKEEP_CONFIG": "your-value"
}
}
}
}ターミナルでこれを実行します
claude mcp add everkeep --env EVERKEEP_VAULT=your-value --env EVERKEEP_CONFIG=your-value -- npx -y everkeep動かす前に、空欄の値を入力してください。
プロジェクトの .cursor/mcp.json、または ~/.cursor/mcp.json に貼り付けます
{
"mcpServers": {
"everkeep": {
"command": "npx",
"args": [
"-y",
"everkeep"
],
"env": {
"EVERKEEP_VAULT": "your-value",
"EVERKEEP_CONFIG": "your-value"
}
}
}
}ブラウザがアプリを開いてよいか確認し、そのあとアプリが設定を表示して確認を求めます。キーの値は空欄のままなので、自分で入力してください。
プロジェクトの .vscode/mcp.json に貼り付けます
{
"servers": {
"everkeep": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"everkeep"
],
"env": {
"EVERKEEP_VAULT": "your-value",
"EVERKEEP_CONFIG": "your-value"
}
}
}
}ブラウザがアプリを開いてよいか確認し、そのあとアプリが設定を表示して確認を求めます。キーの値は空欄のままなので、自分で入力してください。
これはパソコンで動くサーバーですが、ChatGPTがつなげるのはインターネット上のサーバーだけです。ほかのアプリを選んでください。
選んだアプリは、この端末のCookieに保存されます。アカウントは不要です。
EVERKEEP_CONFIG envこの設定は、作者のレジストリ登録情報から作成しています。READMEと違う場合は、READMEに従ってください。
パソコンで動くサーバーです。インストールすると、ツール一覧がAIアプリに表示されます。
誰でも見られる情報をチェックしており、コードは読んでいません。当てはまらない項目は数に入れていません。 · 2026年11月6日にチェック
レジストリ名は、リポジトリを所有するGitHubアカウント st412m で確認済みです
このリポジトリはまだGitHubから読み取っていません
このリポジトリはまだGitHubから読み取っていません
これはパソコンで動くため、インターネット上のエンドポイントはありません
パソコンで動き、代わりにローカルの設定を使います
パソコンで動くサーバーです。ツール一覧を読み取れるのは、インターネット上のエンドポイントがある場合だけです
レジストリでこのカテゴリにある有効なすべてのサーバーと比較しています。スターは、公開者がリポジトリの所有者である場合だけ数えます。
当てはまる基本チェック1項目のうち1項目に合格しました。コードは読んでいません。キーやトークンを追加する前に、サーバーがどんなアクセスを求めているかを確認し、必要な権限だけを持つキーを使ってください。
入力が必要なもの:EVERKEEP_VAULT
あなたのパソコンで動きます。必要なときにAIアプリが起動し、データは作者のサーバーを通りません(サーバー自体がオンラインサービスを呼び出す場合を除きます)。
GitHubリポジトリの最終更新は–、最新バージョン(1.1.0)がレジストリに届いたのは10 日前です。
Claude Desktop、Claude Code、Cursor、VS CodeなどのMCP対応アプリで使えます。パソコンにNode.jsも必要です。
同じカテゴリには:Agent-Native Calendar, Excel MCP Server, MCP Server for Excel
同じカテゴリで、ほかの作者が作ったサーバー。スターの多い順。
カードの見方:★ GitHubスターi3つの柱:レビュー · チェック · 利用状況i更新=最新バージョンをレジストリに公開した日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.
作者のリポジトリから書かれたとおりにコピーしたものです。PopNx MCPは内容を確認・推奨していません。HTML、画像、スクリプトは取り除いています。リンクはこのサイトの外へ移動します。
Stop re-explaining yourself to your AI.
Everkeep keeps your notes, decisions and projects in one folder on your own server. Your AI assistant reads it when a chat starts and writes down what you worked out — so tomorrow's conversation picks up where today's ended. You decide what it may change; it can't delete or overwrite anything you haven't allowed.
Works with Claude and any MCP client · runs on Linux, Docker or Home Assistant
Drop contracts, invoices, manuals, price lists and exported reports into the folder as they are — PDF, Word, Excel, PowerPoint, e-mails. Your AI reads them as text, searches all of them at once and tells you where it found the answer: *"which contract has a 30-day payment term?"* comes back with the file and the page. No uploading files into every chat, no copy-pasting; a new version of a file is read the next time it is needed. Scanned pages it looks at as images.
Files go into the folder by ordinary copying, like into any other folder: see putting your files in.
This gets Everkeep running on your own computer with Docker and connects Claude to it. You need about ten minutes and no programming.
1. Install Docker. On Windows or macOS, install Docker Desktop and start it; wait until it says Docker is running. On Linux, install Docker Engine.
2. Start Everkeep. Open a terminal (on Windows: PowerShell; on macOS: Terminal) and paste the two lines for your system. The first creates the folder everkeep-notes in your home folder; that folder is where your notes will live. The second downloads Everkeep and starts it in the background; it starts again by itself after a reboot.
Windows (PowerShell):
mkdir $HOME\everkeep-notes
docker run -d --name everkeep --restart unless-stopped -p 127.0.0.1:3100:3100 -v "$HOME\everkeep-notes:/vault" -v everkeep-data:/data ghcr.io/st412m/everkeep:1.1.0
macOS or Linux:
mkdir -p ~/everkeep-notes
docker run -d --name everkeep --restart unless-stopped -p 127.0.0.1:3100:3100 -v "$HOME/everkeep-notes:/vault" -v everkeep-data:/data ghcr.io/st412m/everkeep:1.1.0
On Linux the folder must be writable by user id 1000. If the command id -u prints a different number, follow Docker: who owns the folder instead.
3. Protect your notes. One more line, in the same terminal:
docker exec everkeep everkeep policy set . --mode rev --trash
From now on Claude can create new files in the folder, but it can change an existing file only after reading it, so it never overwrites what it has not seen. Nothing is deleted: a file Claude discards goes into the folder .vault-trash inside everkeep-notes, and you can take it back from there.
4. Get your token. Everkeep made a secret token on its first start. Show it:
docker exec everkeep everkeep token
It prints two lines. The first is the secret path for claude.ai, the second the header for other clients:
/private_<token>/mcp
Authorization: Bearer
Treat both like a password: whoever has them can read and change your notes.
5. Connect Claude.
claude mcp add --transport http everkeep http://127.0.0.1:3100/mcp --header "Authorization: Bearer <token>"
https:// /private_ /mcp.6. Try it.
about-me.md with what you know about my current projects."* The file appears in your everkeep-notes folder.explorer $HOME\everkeep-notes in the same PowerShell (or go to This PC → Users → your name → everkeep-notes); on macOS, type open ~/everkeep-notes in Terminal (or Finder → your home folder); on Linux, open your home folder in the file manager.contracts/, projects/….To have Claude read your notes at the start of every chat, add a line like this in Settings → Account → Instructions for Claude, or to a project's instructions: *"At the start of a chat, read /vault/about-me.md with Everkeep."* Inside Docker your folder is /vault.
To change the rules for a folder, see Write policies.
Everkeep is an MCP server. MCP is the way AI clients such as Claude call tools on other machines. Everkeep's tools work on one directory tree, the *vault*: read, search, edit, move and discard files, read documents and PDFs, query SQLite databases read-only. Nothing outside the vault can be reached through it.
What the assistant may change is set per directory with *write policies*: a directory can be read-only, editable only by someone who has read the current version of a file, open to new files only, or free. There is no delete: discarding moves a file into a trash directory of its zone. The assistant cannot change the policies; you set them on the server.
It runs as one process, over HTTP for remote clients such as claude.ai and over stdio for local ones such as Claude Desktop.
The assistant lists a directory. The first line says what is allowed there:
Policy: overwrite=rev, trash=.vault-trash, auto-purge after 30 d — own marker (/vault/wiki/.vault-policy)
[FILE] .vault-policy [DIR] .vault-trash [FILE] decisions.md [FILE] todo.md
It tries to overwrite todo.md without having read it, and is refused:
Error: Refused — policy "overwrite: rev": changing an existing file requires its current rev, which is 5db20d56. Nothing was written. Repeat the call with rev: "5db20d56".
It searches, gets line numbers and the file's rev, and edits one line:
/vault/wiki/todo.md · rev 5db20d56 · 212 lines
148: - [ ] Check backup-rotation settings on the NAS
— 1 match(es) in 1 file(s) · scanned 37/37 files, 190 KB, 12 ms
| Docker | Docker Desktop (Windows, macOS) or Docker Engine (Linux); images for amd64 and arm64 (Raspberry Pi 4/5) |
| Linux without Docker | Node.js ≥ 22.17, poppler-utils (pdfinfo, pdftoppm), sqlite3 |
| Home Assistant | OS or Supervised, through the ha-filesystem-mcp app |
| Disk | the Docker image is about 340 MB; the npm package with its dependencies about 48 MB |
| For claude.ai | a public HTTPS address: see remote access |
The image ghcr.io/st412m/everkeep runs everkeep serve on port 3100 as user id 1000, with the vault at /vault and its own state (token, document cache) in the volume /data. The Quick start shows docker run; compose.example.yaml does the same with Docker Compose. Folder ownership, updates and building the image yourself: installation.
Install poppler-utils and sqlite3 with your package manager, then run it with npx:
npx --yes --package=everkeep everkeep serve --vault /home/me/notes
On first start it prints the token once; everkeep token shows it again. For a permanent everkeep command, a CPU without AVX (some Celeron, Atom and Pentium models) and a systemd service, see installation. Windows and macOS are not supported without Docker.
Install the ha-filesystem-mcp app. It runs Everkeep with the vault under /media or /share and adds the Vault policies page to the sidebar.
Settings come from flags, environment variables and an optional JSON file (EVERKEEP_CONFIG, else ~/.config/everkeep/config.json). The ones to know first:
| Setting | Flag / variable | Default |
|---|---|---|
vault | --vault, EVERKEEP_VAULT | none, required |
host | --host | 127.0.0.1 |
port | --port | 3100 |
state_dir | EVERKEEP_STATE_DIR | ~/.local/state/everkeep |
| token | --token-file, EVERKEEP_TOKEN | generated into /token |
everkeep check-config prints what is in force and checks the tools Everkeep needs. Every key, the token rules and the request log: configuration.
https:// /private_ /mcp. The address must be public HTTPS: remote access. claude mcp add --transport stdio everkeep -- npx --yes --package=everkeep everkeep --vault /home/me/notes
http://127.0.0.1:3100/mcp (or your HTTPS address) with the header Authorization: Bearer , see installation.There is no OAuth: the token is the only key. A wrong path gets an empty 404, a wrong Bearer token 401.
20 tools. Parameters and return formats: tools.
Reading
read_text_file — a whole file, head/tail lines, or an offset/limit range with line count and rev; documents as numbered linesread_multiple_files — several whole files in one responseread_media_file — image or audio as base64read_pdf_text — text of a PDF or a page range, numbered like read_text_fileread_pdf_page — one PDF page rendered as JPEGSearching
grep_files — regex search of file contents, documents included; returns path, rev, line count and matching linessearch_files — find files and directories by nameWriting
write_file — create or overwrite a fileedit_file — literal oldText replacement, or line-addressed edits guarded by revcreate_directory — create a directory and its parentsmove_file — move or rename a file or directory; also restores from the trashcopy_file — copy a file; the destination follows the rules of write_filetrash_file — move a file into its zone's trash; there is no deleteListing
list_directory — entries of one directory, after the policy linelist_directory_with_sizes — entries with file sizes, sorted by name or sizedirectory_tree — tree view, two levels deepget_file_info — size, times and format, plus line count and rev for text files冒頭だけを表示しています。続きはリポジトリで読めます