MCP server Listspace
Commit 12 de nov. de 2026Permite que agentes de IA usem boards do Listspace como memória de projeto para ler e manter quadros de tarefas atualizados.
Também conhecido como listspace/agent, agent
- Stars
- 0
- Ferramentas
- —
- Downloads, 30 dias
- —
- Versão mais recente
- 2.0.0
- Último commit
- 12 de nov. de 2026
- Licença
- MIT
O que é o MCP Listspace?
Listspace é um MCP server. Permite que agentes de IA usem boards do Listspace como memória de projeto para ler e manter quadros de tarefas atualizados.
Resumo gerado a partir do README do projeto
Sobre o MCP server de Listspace
O Listspace oferece uma maneira de agentes de codificação de IA utilizarem boards do Listspace como uma memória de projeto persistente. Isso permite que os agentes leiam quadros de tarefas e os mantenham atualizados enquanto trabalham em uma codebase. O sistema foi projetado para desenvolvedores que utilizam ferramentas como Claude Code ou qualquer agente que suporte o formato Agent Skills. Ele pode ser integrado via um MCP server remoto em mcp.listspace.app ou através de uma CLI local em Node.
Para configurar o servidor, os usuários devem fazer login usando um token de API pessoal obtido nas configurações do Listspace. A implementação inclui um plugin para Claude Code que automatiza o gerenciamento de contexto do board e possui hooks especializados para garantir que o agente registre decisões importantes e atualize o progresso das tarefas. Esses hooks monitoram atividades como edições de arquivos, git commits ou merges de pull requests para incentivar o agente a mover itens no board. A CLI e o plugin foram construídos para ambientes Node.js e oferecem várias formas de gerenciar sessões e interações com os boards.
O que você pode fazer com ele
- 1Registrar decisões importantes do projetoO sistema pode solicitar que um agente documente uma escolha que afete o trabalho de desenvolvimento futuro.
- 2Automatizar a instalação de agent skillsDesenvolvedores podem adicionar rapidamente as capacidades do Listspace a um agente usando um único comando.
Escrito a partir do README do projeto. Cada caso de uso é verificado com uma citação dele.
Como instalar o MCP Listspace
Formatos verificados em 10 nov 2026Adicionar ao CursorAdicionar ao GooseInstalar o MCP Listspace no Claude Code
$ claude mcp add --transport http agent https://mcp.listspace.app/Instalar o MCP Listspace no Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"agent": {
"url": "https://mcp.listspace.app/"
}
}
}Instalar o MCP Listspace no VS Code
.vscode/mcp.json
{
"servers": {
"agent": {
"type": "http",
"url": "https://mcp.listspace.app/"
}
}
}Instalar o MCP Listspace no VS Code CLI
$ code --add-mcp '{"name":"agent","type":"http","url":"https://mcp.listspace.app/"}'Instalar o MCP Listspace no Codex
$ codex mcp add agent --url https://mcp.listspace.app/Instalar o MCP Listspace no Codex config.toml
~/.codex/config.toml
[mcp_servers.agent] url = "https://mcp.listspace.app/"
Instalar o MCP Listspace no Gemini CLI
$ gemini mcp add -s user --transport http agent https://mcp.listspace.app/Instalar o MCP Listspace no Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"agent": {
"url": "https://mcp.listspace.app/",
"type": "http"
}
}
}Verificações automatizadas
Executado em 14 de nov. de 2026Relatório completo →Ainda não verificado. Um servidor precisa de uma pontuação de 80, nenhum problema grave e dados suficientes para verificarmos. Como as verificações funcionam · O que corrigir para ganhar mais pontos
- Repositório de origem vinculado e acessívellistspace/agent is public and reachablegithub.com/listspace/agent ↗Passou
- O pacote indica este repositório como sua origemNão verificado
- Proveniência da build (atestação Sigstore)Não verificado
- Licença de código aberto (OSI)MITspdx.org/licenses/MIT.html ↗Passou
- Commit ou release no último anoLast commit or release 2026-11-12github.com/listspace/agent ↗Passou
- OpenSSF ScorecardNão verificado
- Nome do pacote não é próximo a um pacote popularNão verificado
- Nenhum aviso crítico no pacote ou em suas dependênciasNão verificado
- Sem instruções ocultas para o modelo0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPassou
- Ferramentas destrutivas estão rotuladasNão verificado
- O endpoint remoto responde ao handshake do MCPHTTPS endpoint answered 401 (sign-in required)Passou
README
Ver no GitHubListspace 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).
Perguntas sobre o MCP Listspace
Como adiciono o MCP Listspace ao Claude Code?
Execute claude mcp add --transport http agent https://mcp.listspace.app/ no seu terminal. Adicione --scope user para torná-lo disponível em todos os projetos.
Como adiciono o MCP Listspace ao Cursor?
Abra ~/.cursor/mcp.json e adicione o servidor em mcpServers, usando a configuração do Cursor mostrada na seção de instalação acima.
Posso usar o Listspace com o Claude Code?
Sim, existe um plugin dedicado para o Claude Code que registra o MCP server remoto e inclui hooks especializados para rastreamento de decisões e progresso.
Como funciona a verificação de progresso?
A verificação de progresso monitora se um agente realizou tarefas como edições de arquivos ou git commits sem atualizar o board do Listspace, incentivando o agente a registrar a atualização.