Listspace
app.listspacev2.0.0Updated Oct 8, 2026
Project memory for AI agents: read and keep the user's Listspace boards up to date.
Overview
Lets an AI assistant read and update the user's Listspace boards as project memory for coding work.
- What it does
- Listspace is a remote MCP server that exposes the user's Listspace boards to an assistant, so a board can act as project memory. The README describes a companion skill and a Node CLI over the same REST API, with commands such as login, whoami, session, add and attach. The CLI can add items and attach files from disk, and every command supports JSON output.
- When to use it
- Use it when a coding agent should keep a Listspace board up to date as it works, or read that board for context. It suits teams already using Listspace boards for project tracking.
- Requirements
- A remote endpoint at mcp.listspace.app; no packages, environment variables or headers are declared in the manifest. The README says sign-in is OAuth through the MCP client, or a personal token from Listspace Settings > API for the CLI. The CLI needs Node 20 or later; LISTSPACE_TOKEN and LISTSPACE_API_URL are optional overrides.
Installation
In SourceWeft
- Open Listspace in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Other MCP clients
Add this to your client's mcpServers config.
{
"mcpServers": {
"listspace": {
"type": "http",
"url": "https://mcp.listspace.app"
}
}
}README
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:
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:
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
npm link in agent/cli puts listspace on the PATH. LISTSPACE_TOKEN overrides the saved token for one run, and LISTSPACE_API_URL points 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:
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:
Or as a local marketplace, which keeps it installed:
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.
What is left out, and why
comment: the API has it (POST /v1/items/:id/comments, MCPadd_comment), but the CLI does not yet. Agents on the CLI log progress in a Project info item (the skill says so).attachis in the CLI since 0.2.0, because a file on disk is the one thing an agent cannot send reliably through MCP.- Device pairing for
login: comes with sign-up (PR 9).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(0.1.0). 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).
Source: README.md at commit c98198a
Tools
0Version history
1- v2.0.0LatestOct 8, 2026
