# Base de Conhecimento Muse connector

From musedirectory.ai, the independent directory of Meta Muse connectors. Not affiliated with Meta.

## Base de Conhecimento

Upload and search your personal documents, notes, and files with semantic search.

- Record: https://musedirectory.ai/connector/base-de-conhecimento
- Category: Productivity
- Developer: mcp.ai
- Muse status: Extra setup. Not in Muse's Connectors list yet. Muse can still use it: its page gives you a request to paste into Muse.
- Health: Working, 494ms, checked 2026-09-28T07:31:08Z
- Endpoint: https://api.mcp.ai/p_kb
- Auth: No account needed; Pricing: unknown
- Screening: Screened, no issues found (2026-09-25T10:51:17Z)
- Source: Found in the official MCP Registry (io.github.mcp-dir/kb-mcp) https://registry.modelcontextprotocol.io/v0/servers?search=io.github.mcp-dir%2Fkb-mcp

A private knowledge base that indexes documents (markdown, text, Word, PDF, images) and lets you search them semantically. Upload files or paste text, then retrieve relevant excerpts to use as context for your tasks.

Example request: "Search my uploaded meeting notes to find what we decided about the Q3 budget."

How to connect: Not in Muse's Connectors list yet, but Muse can still use it. Paste this into Muse: "Use Base de Conhecimento to help me. It is a free service with an MCP server at https://api.mcp.ai/p_kb. It does not need an API key. Ask me before you share anything with it." Muse asks before it shares anything with the app's site. Meta does not review apps used this way, so only use ones you trust. We tested this in the Muse app on September 24, 2026: Muse used an app's link directly this way and returned a live answer.

Tools:
- kb_search: Busca semântica na base de conhecimento. Devolve os trechos (chunks) mais relevantes pra usar como contexto, com nome do arquivo de origem e score. Retrieval-only: você sintetiza a resposta a partir dos trechos.
- kb_list_documents: Lista os documentos da base (id, nome, status, tamanho, nº de chunks).
- kb_get_document: Metadados + status de um documento específico (sem o texto cru). Bulk support: accepts document_ids for batched execution.
- kb_add_text: Adiciona um texto colado à base (vira um documento indexado e buscável). Útil pra notas, trechos, anotações.
- kb_ingest_url: Baixa um arquivo de uma URL (.md/.txt/.docx) e o indexa na base. Bom pra ingerir um documento remoto sem upload manual.
- kb_remove_document: Remove um ou mais documentos da base (apaga o original, os chunks e o índice). Aceita uma lista de ids.
- kb_list_accounts: Lista as bases de conhecimento conectadas neste install. Retorna cada base com id, rótulo e um flag is_default (true quando só há uma — não precisa passar `account` nas outras tools). Com várias bases, toda kb_* aceita um `account` opcional (id ou rótulo).
- show_version: Show the current MCP platform and adapter versions.
- report_bug: Report a bug, missing feature, or send feedback. Include the conversation array with recent messages for reproduction.
- connect: Returns connection status and URLs. When all providers are connected, returns authenticated:true and empty pending[]. When credentials are missing, returns connect_url for the toolkit and per-install URLs.
- toolkit_info: Returns the current toolkit state: installed MCPs, their connection status, the accounts connected to each one, and how many catalog tools each exposes.
- marketplace: The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them. Covers capability requests like "find an MCP that does X", "consulta um CPF", "is there a tool for Y". Core flow: action=search discovers MCPs by intent → describe returns one MC
- authenticate: MCP.AI for IDE agents (Cursor, etc.): log in in the browser, copy the access token. Best: add it to this server's config as a header `Authorization: Bearer <token>` for a permanent, non-expiring connection. Or paste it here for a session-only login: call with { token: "<jwt>" } a

Screening checks:
- MCP handshake: pass (Answered in 232ms)
- Domain against threat feeds (Cloudflare security DNS): pass (api.mcp.ai not flagged)
- Published packages against the OSV malicious-package database: n/a (No npm or PyPI package published)
- Hidden instructions or invisible characters in tool text: pass (13 tools read, nothing found)
- Inputs asking for passwords, card numbers or seed phrases: pass (None found)
- Domain and redirects: pass (Domain registered 2777 days ago)
- AI review of purpose and tool behavior: pass (No concerns)
