Skip to main content
ClaudeWave

Cursor plugin for teamshared: remote MCP + recall-first memory rule

MCP ServersRegistry oficial0 estrellas0 forksShellMITActualizado today
ClaudeWave Trust Score
87/100
Trusted
Passed
  • Open-source license (MIT)
  • Actively maintained (<30d)
  • Clear description
  • Documented (README)
Last scanned: 8/19/2026
Install in Claude Code / Claude Desktop
Method: Manual
Claude Code CLI
git clone https://github.com/teamshared-ai/teamshared-plugin
1. Run the command above in your terminal (Claude Code), or paste the JSON config into claude_desktop_config.json (Claude Desktop).
2. Replace any <placeholder> values with your API keys or paths.
3. Restart Claude. The MCP server and its tools appear automatically.
💡 Clone https://github.com/teamshared-ai/teamshared-plugin and follow its README for install instructions.
Casos de uso

Resumen de MCP Servers

# teamshared (Cursor plugin)

Registers the teamshared MCP server and ships the recall-first memory rule.
Nothing else — no skills, slash commands, hooks, or continual-learning agent.

The MCP server itself lives in [`xhad/teamshared`](https://github.com/xhad/teamshared)
and is hosted at [teamshared.com](https://teamshared.com).

| Component | Purpose |
|---|---|
| `mcp.json` | Registers `https://teamshared.com/mcp` (URL only; Cursor OAuth Connect) |
| `rules/teamshared.mdc` | Lean always-on fetch/store loop (`alwaysApply`); tool encyclopedia lives in `memory_tools_catalog` |
| `clients/` | Copy-paste protocol + MCP examples for non-Cursor harnesses (not loaded by Cursor) |

## Install

### From marketplace (recommended)

1. **Settings → Plugins → Add marketplace** → `https://github.com/teamshared-ai/teamshared-plugin`
2. Run **`/add-plugin teamshared`** or enable it under Settings → Plugins
3. **Settings → Tools & MCP → teamshared → Connect** (email + one-time code, same as the console)

For [cursor.directory](https://cursor.directory/plugins/new), submit this same repo URL. Root `plugin.json` and `.mcp.json` are the Open Plugins / directory discovery files; Cursor install still uses `.cursor-plugin/` and `mcp.json`.

Installing the plugin registers the MCP server. You only click **Connect** —
do not paste a URL or `tsk_*` token into `mcp.json`.

See [MARKETPLACE.md](MARKETPLACE.md) for publish/submission checklist.

### From this repo (folder or symlink)

**Add plugins from folder** needs a marketplace catalog in the selected
directory. Select **this repo root** (it ships `.cursor-plugin/marketplace.json`
with `"source": "./"`).

Then enable the plugin, reload the window, and **Connect**.

For local iteration without the folder picker:

```bash
ln -sf "$(pwd)" ~/.cursor/plugins/local/teamshared
```

## Setup

1. **Connect with email/OTP** — **Settings → Tools & MCP → teamshared → Connect**.
   Cursor opens a browser; sign in with the same email + one-time code as the
   web console (`/app`). The plugin already shipped the server URL; do not add
   headers or a `tsk_*` token.
2. **Developer: Reload Window** — confirm **Settings → MCP** shows `teamshared` enabled.

If you previously added `https://teamshared.com/mcp` by hand, remove that
manual entry so you do not get two `teamshared` servers.

API keys (`tsk_…` under `/app/keys`) remain for CI and non-Cursor harnesses.

## What you get

- **MCP tools**: `memory_recall`, `memory_remember`, `memory_session_*`, etc.
  (registered by `mcp.json` when the plugin is installed).
- **Rule**: injects the recall-first protocol on every agent turn, and points
  teammates to the web console (`/app`) for human actions.

Session logging and context compression live in the MCP tools and the rule —
not in Cursor hooks.

## Other clients

See [`clients/`](clients/) for Hermes, Claude Desktop, and protocol markdown.

## License

MIT — see [LICENSE](LICENSE).

Lo que la gente pregunta sobre teamshared-plugin

¿Qué es teamshared-ai/teamshared-plugin?

+

teamshared-ai/teamshared-plugin es mcp servers para el ecosistema de Claude AI. Cursor plugin for teamshared: remote MCP + recall-first memory rule Tiene 0 estrellas en GitHub y su última actualización registrada es del 2026-08-18.

¿Cómo se instala teamshared-plugin?

+

Puedes instalar teamshared-plugin clonando el repositorio (https://github.com/teamshared-ai/teamshared-plugin) o siguiendo las instrucciones del README en GitHub. ClaudeWave también te ofrece bloques de instalación rápida en esta misma página.

¿Es seguro usar teamshared-ai/teamshared-plugin?

+

Nuestro agente de seguridad ha analizado teamshared-ai/teamshared-plugin y le ha asignado un Trust Score de 87/100 (tier: Trusted). Revisa el desglose completo de comprobaciones superadas y flags en esta página.

¿Quién mantiene teamshared-ai/teamshared-plugin?

+

teamshared-ai/teamshared-plugin es mantenido por teamshared-ai. La última actividad registrada en GitHub es del 2026-08-18, con 0 issues abiertos.

¿Hay alternativas a teamshared-plugin?

+

Sí. En ClaudeWave puedes explorar mcp servers similares en /categories/mcp, ordenados por popularidad o actividad reciente.

Despliega teamshared-plugin en tu cloud

Lleva este repo a producción en minutos. Cada plataforma genera su propio entorno con variables de entorno editables.

¿Mantienes este repo? Añade un badge a tu README

Pega el badge en tu README de GitHub para mostrar que está auditado por ClaudeWave. Cada badge enlaza de vuelta a esta página y muestra el Trust Score actual.

Featured on ClaudeWave: teamshared-ai/teamshared-plugin
[![Featured on ClaudeWave](https://claudewave.com/api/badge/teamshared-ai-teamshared-plugin)](https://claudewave.com/repo/teamshared-ai-teamshared-plugin)
<a href="https://claudewave.com/repo/teamshared-ai-teamshared-plugin"><img src="https://claudewave.com/api/badge/teamshared-ai-teamshared-plugin" alt="Featured on ClaudeWave: teamshared-ai/teamshared-plugin" width="320" height="64" /></a>

Más MCP Servers

Alternativas a teamshared-plugin