convez.ai
MCP ServerProdutividadeIntermediário
hoornet

AgentDocs MCP Server

hoornet/agentdocs-mcp

Documentação colaborativa nativa para agentes de IA

Ver no GitHub
InicialPluginScore · de 0 a 100

Servidor MCP que conecta agentes de IA ao AgentDocs, plataforma colaborativa de documentação. Fornece ferramentas nativas para ler, buscar, criar, atualizar e compartilhar documentos de forma integrada em ferramentas como Claude Desktop, Cursor e Windsurf.

Instalação

$npx convez-ai hoornet/agentdocs-mcp

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
1
Forks
0
Acompanhando
0
Saúde
57%
Último commit
há 5 dias
Versão
v0.11.0
Issues abertas
0
Contribuidores
1

Casos de uso

  • Agentes criando e atualizando documentação em tempo real
  • Busca semântica e full-text em bases de conhecimento
  • Importação em lote de arquivos Markdown com versionamento
  • Compartilhamento automático de páginas com links públicos
  • Integração de logs e relatórios em documentos colaborativos

Veredito

MCP server bem estruturado para ambientes que usam AgentDocs como hub de documentação colaborativa. Cobertura completa de operações CRUD com suporte a busca semântica (Pro) e tokens scoped. Setup direto via npx e boa documentação de configuração em múltiplas IDEs.

README

A tradução para o português deste README ainda está na fila.

agentdocs-mcp

MCP server for AgentDocs — the collaborative documentation platform where AI agents are first-class citizens.

Gives MCP clients that run a local server (Claude Code, Claude Desktop, Cursor, Windsurf, Zed, …) native tools to read, search, create, update, and share AgentDocs pages.

Claude.ai (web) can't run a local stdio server — add the hosted Skill (Skills → Upload Skill) instead. A hosted remote MCP connector for Claude.ai is on the roadmap.

Setup

You need an AgentDocs API token:

  • Account token — agentdocs.eu → Profile → Regenerate API Token (full access to everything you own), or
  • Space token — Space settings → Tokens (editor access to exactly one space; the server auto-detects this and scopes itself to that space — the recommended way to sandbox an agent).

Claude Code

claude mcp add agentdocs --env AGENTDOCS_TOKEN=<your-token> -- npx -y agentdocs-mcp

Cursor / Windsurf / generic MCP config

{
  "mcpServers": {
    "agentdocs": {
      "command": "npx",
      "args": ["-y", "agentdocs-mcp"],
      "env": { "AGENTDOCS_TOKEN": "<your-token>" }
    }
  }
}

Opencode

In opencode.json (project root) or ~/.config/opencode/opencode.json:

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "agentdocs": {
      "type": "local",
      "command": ["npx", "-y", "agentdocs-mcp"],
      "environment": { "AGENTDOCS_TOKEN": "<your-token>" }
    }
  }
}

Configuration

Env varDefaultPurpose
AGENTDOCS_TOKENcontents of ~/.config/agentdocs/tokenAPI token (account or space-scoped)
AGENTDOCS_URLhttps://agentdocs.euPoint at a self-hosted AgentDocs instance

Tools

ToolDescription
whoamiIdentify the user and credential scope
list_workspacesList accessible workspaces ¹
list_spacesList spaces in a workspace ¹
list_pagesPage tree of a space (without content)
search_docsFull-text (keyword) search across a workspace ¹
semantic_searchNatural-language search ranked by meaning — Pro workspaces ¹
get_pageRead a page (full Markdown + version); optional include_comments
create_pageCreate a Markdown page (nestable)
update_pageUpdate title/content, with optional optimistic version check
append_to_pageAppend Markdown — ideal for logs and session reports
import_markdownImport a folder of Markdown files; paths become the page hierarchy. Idempotent — re-import reuses by source path (no duplicates); parent_page anchor + overwrite_existing re-sync
delete_pageDelete a page (cascades to children)
bulk_create_pagesCreate up to 500 pages atomically with explicit structure
share_pageCreate a public magic link (web + raw-Markdown URLs)

¹ Hidden when running with a space-scoped token.

Pages, spaces, and workspaces are addressable by UUID or human-readable slug path — get_page accepts "my-workspace/my-space/my-page", create_page accepts "my-workspace/my-space", etc. (Slug paths require an account token.)

Notes

  • Every page update creates a version on the server; old versions stay restorable from the AgentDocs UI.
  • The hosted instance may take ~15 s to respond to the first request after being idle (database cold start) — the server absorbs this with a 35 s timeout and one retry.
  • Free-tier API limits surface as clear messages with an upgrade link.

Development

npm install
npm run build

# End-to-end smoke tests (hit a real AgentDocs instance with YOUR data):
SMOKE_TESTBED_SPACE="workspace-slug/scratch-space-slug" \
SMOKE_KNOWN_PAGE="workspace-slug/space-slug/page-slug" \
node test/smoke.mjs                       # account token: all tools

AGENTDOCS_TOKEN=<space-token> node test/smoke-space-token.mjs   # space-token mode

The testbed space is written to (pages created and deleted) — use a scratch space.

Security

See SECURITY.md. Report vulnerabilities privately to contact@agentdocs.eu.

License

MIT

Ver o original no GitHub

Bom para

Relacionados