Listspace MCPサーバー
コミット 2026年11月12日AIエージェントがListspaceボードをプロジェクトメモリとして利用し、タスクボードの読み取りや最新状態への更新を行えるようにします。
別名 listspace/agent, agent
- スター
- 0
- ツール
- —
- ダウンロード数(30日間)
- —
- 最新バージョン
- 2.0.0
- 最終コミット
- 2026年11月12日
- ライセンス
- MIT
Listspace MCPとは
ListspaceはMCPサーバーです。 AIエージェントがListspaceボードをプロジェクトメモリとして利用し、タスクボードの読み取りや最新状態への更新を行えるようにします。.
プロジェクトのREADMEから生成された概要
Listspace MCP server について
Listspaceは、AIコーディングエージェントがListspaceボードを永続的なプロジェクトメモリとして利用できる仕組みを提供します。これにより、エージェントはタスクボードを読み取り、コードベースでの作業を進めながらボードを最新の状態に保つことができます。このシステムは、Claude Codeなどのツールや、Agent Skills形式をサポートするあらゆるエージェントを使用する開発者向けに設計されています。mcp.listspace.appにあるリモートMCP server経由、またはローカルのNode CLIを通じて統合可能です。
サーバーをセットアップするには、Listspaceの設定から取得したパーソナルAPI tokenを使用してサインインする必要があります。実装には、ボードのコンテキスト管理を自動化するClaude Codeプラグインが含まれており、エージェントが重要な決定を記録し、タスクの進捗を更新することを確実にするための専用フックが備わっています。これらのフックは、ファイルの編集、git commit、プルリクエストのマージなどのアクティビティを監視し、エージェントにボード上のアイテムを移動するよう促します。CLIとプラグインはNode.js環境向けに構築されており、セッションやボードとのやり取りを管理するためのさまざまな方法を提供します。
できること
- 1重要なプロジェクトの決定事項を記録する将来の開発作業に影響を与える選択について、エージェントにドキュメント化を促すことができます。
- 2エージェントのスキルインストールを自動化する開発者は単一のコマンドを使用して、エージェントにListspaceの機能を素早く追加できます。
プロジェクトの README から作成されています。すべてのユースケースは、その引用と照らし合わせて確認されています。
Listspace MCPのインストール方法
フォーマット検証日 2026年11月10日Cursor に追加Gooseに追加Claude CodeにListspace MCPをインストール
$ claude mcp add --transport http agent https://mcp.listspace.app/CursorにListspace MCPをインストール
~/.cursor/mcp.json
{
"mcpServers": {
"agent": {
"url": "https://mcp.listspace.app/"
}
}
}VS CodeにListspace MCPをインストール
.vscode/mcp.json
{
"servers": {
"agent": {
"type": "http",
"url": "https://mcp.listspace.app/"
}
}
}VS Code CLIにListspace MCPをインストール
$ code --add-mcp '{"name":"agent","type":"http","url":"https://mcp.listspace.app/"}'CodexにListspace MCPをインストール
$ codex mcp add agent --url https://mcp.listspace.app/Codex config.tomlにListspace MCPをインストール
~/.codex/config.toml
[mcp_servers.agent] url = "https://mcp.listspace.app/"
Gemini CLIにListspace MCPをインストール
$ gemini mcp add -s user --transport http agent https://mcp.listspace.app/Gemini settings.jsonにListspace MCPをインストール
~/.gemini/settings.json
{
"mcpServers": {
"agent": {
"url": "https://mcp.listspace.app/",
"type": "http"
}
}
}自動チェック
実行日 2026年11月14日完全なレポート →まだ検証されていません。サーバーには80点のスコア、重大な問題がないこと、および検証に必要な十分なデータが必要です。 チェックの仕組み · 点数を上げるための改善点
- ソースリポジトリがリンクされており、アクセス可能listspace/agent is public and reachablegithub.com/listspace/agent ↗合格
- パッケージがこのリポジトリをソースとして指定未チェック
- ビルドの来歴 (Sigstore 証明)未チェック
- オープンソースライセンス (OSI)MITspdx.org/licenses/MIT.html ↗合格
- 過去1年以内にコミットまたはリリースありLast commit or release 2026-11-12github.com/listspace/agent ↗合格
- OpenSSF Scorecard未チェック
- パッケージ名が有名なパッケージに酷似していない未チェック
- パッケージおよびその依存関係に重大な勧告なし未チェック
- モデルへの隠れた指示がない0 tool descriptions and the README read; no override phrases, credential paths or hidden characters合格
- 破壊的なツールがラベル付けされている未チェック
- リモートエンドポイントが MCP ハンドシェイクに応答HTTPS endpoint answered 401 (sign-in required)合格
README
GitHubで見るListspace for coding agents
The pieces that let an agent use a Listspace board as its project memory. This folder is public as github.com/listspace/agent, and the CLI is on npm as listspace. Install and sign in with:
npx listspace login # paste a personal token from Listspace: Settings > Your AI > API tokens
npx listspace boards
| Path | What it is |
|---|---|
skills/listspace/ |
The skill: SKILL.md (the work loop) plus reference/ (tools, agent access, CLI), loaded only when needed. Follows the Agent Skills format, so npx skills add can install it. This is the source copy. |
cli/ |
listspace, a small Node CLI for agents without the MCP server: short commands over the REST API (https://api.listspace.app/v1), and call for every MCP tool through the MCP server (https://mcp.listspace.app). TypeScript bundled into one ESM file, no runtime dependencies, Node 20 or later. |
claude-code-plugin/ |
A Claude Code plugin: the skill (a copied file set) and .mcp.json, which registers the remote MCP server https://mcp.listspace.app. |
.claude-plugin/marketplace.json |
A marketplace file listing the plugin, so this folder can be added as a local marketplace now and as a GitHub one later. |
AGENTS.md.snippet |
Lines a user pastes into a repo's AGENTS.md or CLAUDE.md to point agents at the right board. |
scripts/ |
sync-skill.mjs copies the skill into the plugin; check-agent.mjs (in CI) checks the copy, the frontmatter, the versions and the MCP entry. |
The MCP server is also listed in the MCP Registry as app.listspace/listspace and on Smithery.
Editing the skill
Edit skills/listspace/ only, then run:
node agent/scripts/sync-skill.mjs
node agent/scripts/check-agent.mjs
The plugin gets a real copy, not a symlink, so the plugin folder still works when it is copied or downloaded on its own. CI fails when the two differ. Keep SKILL.md short: steps and rules there, detail in reference/.
One version runs through cli/package.json, cli/src/version.ts, plugin.json and the skill's metadata.version; the check fails when they differ.
Try it locally
The CLI
cd agent/cli
npm ci
npm run build
node dist/listspace.mjs login # paste a token from Listspace: Settings > Your AI > API tokens
node dist/listspace.mjs whoami
node dist/listspace.mjs session "<board title or id>"
node dist/listspace.mjs add "<board>" ideas "Try dark mode" --description "Seen in **settings**"
npm link in agent/cli puts listspace on the PATH. LISTSPACE_TOKEN overrides the saved token for one run, and LISTSPACE_API_URL and LISTSPACE_MCP_URL point the CLI at another server. Every command takes --json. The token is saved in the OS config directory (%APPDATA%\listspace on Windows, ~/Library/Application Support/listspace on macOS, ~/.config/listspace elsewhere) as credentials.json, mode 600.
Tests: npm test (node:test with a fake fetch, no network). npm run typecheck runs the strict type check.
The skill on its own
Any agent that reads Agent Skills:
npx skills add ./agent -s listspace # the skills CLI reads skills/ in a local folder
or copy agent/skills/listspace to ~/.claude/skills/listspace for Claude Code. Connect the MCP server separately (claude mcp add --transport http listspace https://mcp.listspace.app), or use the CLI above.
The Claude Code plugin
For one session:
claude --plugin-dir ./agent/claude-code-plugin
Or as a local marketplace, which keeps it installed:
claude plugin marketplace add ./agent
claude plugin install listspace@listspace
Then run /mcp, pick the listspace server and sign in (OAuth through Listspace). The skill shows up as /listspace:listspace and Claude loads it on its own when the project has a board. claude plugin validate ./agent/claude-code-plugin checks the manifest.
If you already added the Listspace MCP server yourself, Claude Code may show both; remove one.
The decision check
The plugin also has a small check that runs at the end of each of Claude's turns (hooks/hooks.json, hooks/decision-check.mjs). When the user picks an option, says yes to a proposal or corrects a fact, and Claude records no decision in that turn, Claude is sent back once with one line: if it was a decision that affects future work, record it with record_decision as Proposed; otherwise end the turn without comment.
The rules lean to silence. A yes to an offer to act ("Want me to commit?" "yes"), a maybe, and a bug report or a place in the code ("no, it's still failing", "the bug is in the parser") are not decisions. A yes counts only when Claude's last message offered a choice or made a proposal (recommend, suggest, propose, options, which one, a lettered list).
- It does nothing in a session that has not used a Listspace tool, and never blocks twice in a turn (
stop_hook_active), so it cannot loop. - It is plain rules on the user's words, with no model call and no network, so it costs nothing and answers in milliseconds (timeout 5 seconds).
- It needs Node.js 18 or later on the computer (Windows, macOS or Linux). Each command ends in
; exit 0, so without Node.js the check does nothing and Claude Code shows no hook error (sh, Git Bash and PowerShell). - It keeps a few small files per session in the plugin's data folder (
CLAUDE_PLUGIN_DATA, readable only by the user) and removes them after a week. An ordinary prompt writes nothing. A prompt that reads like a decision leaves its first line, cut at 80 characters, for that turn only. Of Claude's last message it keeps only whether it offered a choice. Without the data folder the check does nothing. - Tests:
node --test agent/scripts/decision-check.test.mjs.check-agent.mjscheckshooks.json.
The progress check
A second check at the end of each turn (hooks/progress-check.mjs) keeps the board in step with the work. When a turn changed files (Edit, Write, MultiEdit, NotebookEdit), committed, pushed or merged with git, opened or merged a pull request with gh, or deployed, and Claude made no Listspace write after that work, Claude is sent back once with one line: "Update the Listspace board: what did you start or finish this turn? Move the item, add a short comment."
- It does nothing in a session that has not used a Listspace tool, and never blocks twice in a row (
stop_hook_active), so it cannot loop. - After a nudge it waits at least 3 turns before the next one, and only nudges again for new work, so it does not nag.
- Any Listspace write counts as the update (
move_item,add_comment,complete_item,record_decision,captureand the rest); reads do not. - It keeps only the facts (work done, board updated, the turn of the last nudge) in the plugin's data folder, never a command or a file name, and removes them after a week. Same Node.js and
; exit 0rules as the decision check. - Tests:
node --test agent/scripts/progress-check.test.mjs.
Board context
The board rules arrive with the Listspace server's instructions at the start of a session, and a long session, most of all one whose conversation was compacted, can lose them. hooks/board-hooks.mjs adds them back to Claude's context at the moments that matter. It only adds context: it never blocks anything and never changes a command or its output.
- Session start (SessionStart: startup, resume, clear): one line that names the project's board and says to start with
get_accountandstart_session, update the items inunfinished_from_last_sessionsfirst, and keep the board current. - After a compaction (SessionStart with source
compact): the board rule, and to callget_account(orstart_session) before going on, sinceclaimed_by_youandstarted_by_youlist the items Claude was working on. - After a pull request or a deploy (PostToolUse on Bash and PowerShell): after
gh pr create,gh pr mergeor a deploy command that worked, one line says to move the matching item (to Doing for a new pull request, to Done after a merge or a deploy) and add a short comment. - It does this only in a project whose CLAUDE.md or AGENTS.md has a
Listspace board:line (in the folder or one above it, up to the repository root), or in a session that used a Listspace tool (the progress check's note). From the file it takes only a link to a Listspace board, never other text. - It writes nothing and makes no network call. Same Node.js and
; exit 0rules as the decision check. - Tests:
node --test agent/scripts/board-hooks.test.mjs.
What is left out, and why
- Device pairing for
login: the API has it (POST /auth/device), but the CLI does not use it yet.loginalready separates "how the token is obtained" from saving it; a TODO incli/src/cli.tsmarks where pairing goes.--tokenand a piped token stay for scripts. - A token in the plugin:
.mcp.jsonhas no headers on purpose. A token would ship to every user; sign-in through/mcpis per user. The check script refuses headers there. - The CLI inside the plugin (
bin/): left out, because claude.ai and Cowork do not install plugins with a top-levelbin/and the MCP server covers Claude Code.
Publishing
- Skill via
npx skills add: published. The public repositorylistspace/agentholds this folder at its root, sonpx skills add listspace/agentworks. - CLI on npm: published as the unscoped
listspace(0.6.0). To release a new version: bump the one version (see "Editing the skill"), check the package contents withnpm pack --dry-run, thennpm publishfromagent/cliwith an npm account with 2FA.prepublishOnlyruns the type check, tests and build. - Claude Code plugin: the public repo doubles as a marketplace (
.claude-plugin/marketplace.json), so users run/plugin marketplace add listspace/agentand/plugin install listspace@listspace. Listing in Anthropic's plugin directory is a separate submission; the owner decides on it, with privacy policy and terms URLs for that listing.
Sources: Claude Code plugin manifest reference (https://code.claude.com/docs/en/plugins-reference), plugin loading and --plugin-dir (https://code.claude.com/docs/en/plugins/loading), marketplace reference (https://code.claude.com/docs/en/plugins/marketplace-reference), skills (https://code.claude.com/docs/en/skills), Agent Skills specification (https://agentskills.io/specification), the skills CLI (https://github.com/vercel-labs/skills), and Postiz's agent repo as the model (https://github.com/gitroomhq/postiz-agent).
Listspace MCPのよくある質問
Listspace MCPをClaude Codeに追加するには
ターミナルでclaude mcp add --transport http agent https://mcp.listspace.app/を実行します。すべてのプロジェクトで利用するには--scope userを追加します。
Listspace MCPをCursorに追加するには
~/.cursor/mcp.jsonを開き、上記のインストールセクションに示すCursor設定を使ってmcpServersの下にサーバーを追加します。
Claude CodeでListspaceを使用できますか?
はい。専用のClaude Codeプラグインが用意されており、リモートMCP serverを登録して、意思決定や進捗管理のための専用フックを利用できます。
進捗チェックはどのように機能しますか?
進捗チェックは、エージェントがファイルの編集やgit commitなどの作業を行ったにもかかわらず、Listspaceボードを更新していない場合にそれを検知し、エージェントに更新を記録するよう促します。