Os detalhes de cada servidor, incluindo portas, repositórios e ferramentas, permanecem os mesmos. As configurações de ambiente agora são gerenciadas
If you want an AI assistant working directly with MCP Stack, the mcp stack mcp server is the bridge. Os detalhes de cada servidor, incluindo portas, repositórios e ferramentas, permanecem os mesmos. As configurações de ambiente agora são gerenciadas centralmente.
Os detalhes de cada servidor, incluindo portas, repositórios e ferramentas, permanecem os mesmos. As configurações de ambiente agora são gerenciadas centralmente.
Once connected, the assistant can call these 4 tools directly:
filesystem — mcp monta apenas a pasta do projeto – evite expor ~/ completoArquivo — Funçãodocker-compose.yml — Definição do container + volumes + portasREADME.md — Link upstream + instruções específicasSetup follows the standard MCP pattern: clone or install the server, then register it in your client's configuration file and restart the client. The configuration snippets on this page cover Claude Desktop, Claude Code and Cursor.
Before the server will start you need to supply 3 environment variables: VAULT_PATH, ZOTERO_API_KEY, ZOTERO_USER_ID. Keep credentials in your client's env block or a secrets manager rather than committing them.
Cloud and DevOps servers put infrastructure on speaking terms with your assistant, so "why is this broken?" is answered from real state rather than a generic checklist. MCP Stack sits in that group, and the shape of its toolset — filesystem, Arquivo, docker-compose.yml among others — tells you what it is really for. Worth comparing against the other cloud devops servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.
| Tool | What it does |
|---|---|
| filesystem | mcp monta apenas a pasta do projeto – evite expor ~/ completo. |
| Arquivo | Função |
| docker-compose.yml | Definição do container + volumes + portas |
| README.md | Link upstream + instruções específicas |
{
"mcpServers": {
"memory": { "url": "http://localhost:9100" },
"github": { "url": "http://localhost:9101" },
"filesystem": { "url": "http://localhost:9102" },
"supabase": { "url": "http://localhost:9103" },
"obsidian": { "url": "http://localhost:9104" },
"zotero": { "url": "http://localhost:9107" },
"docgen": { "url": "http://localhost:9105" },
"hugo": { "url": "http://localhost:9106" },
"ollama": { "url": "http://localhost:9108" },
"fabric": { "url": "http://localhost:9109" }
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| VAULT_PATH | Filesystem location the server is allowed to use. | Optional |
| ZOTERO_API_KEY | Credential the server authenticates with. | Yes |
| ZOTERO_USER_ID | Configuration value read at startup. | Optional |
Manage your whole Supabase project in conversation — database, auth, storage, Edge Functions and branches.
Stop letting your assistant hallucinate n8n node parameters — this server hands it the real schemas, templates and validation.
AWS Labs' official server suite — current AWS docs, CDK guidance, cost analysis and service tools.
Cloud browsers for AI agents — automation sessions that run in Browserbase's fleet, not on your machine.
Workers, KV, R2 and D1 by conversation — Cloudflare's official remote servers for building and observability.
Dashboards, Prometheus and Loki queries, incidents and alerts — observability by conversation.