Your private knowledge base: upload documents (.md, .txt, .docx, PDF, images), the platform indexes everything semantically and the agent retrieves the relevant context on demand. Built for firms. Each base is isolated, content stays encrypted on the
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add --transport http base-de-conhecimento https://api.mcp.ai/p_kb~/.codex/config.toml
[mcp_servers.base-de-conhecimento]
url = "https://api.mcp.ai/p_kb"
# codex mcp add base-de-conhecimento --url https://api.mcp.ai/p_kb~/.cursor/mcp.json
{
"mcpServers": {
"base-de-conhecimento": {
"url": "https://api.mcp.ai/p_kb"
}
}
}.vscode/mcp.json
{
"servers": {
"base-de-conhecimento": {
"type": "http",
"url": "https://api.mcp.ai/p_kb"
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"base-de-conhecimento": {
"httpUrl": "https://api.mcp.ai/p_kb"
}
}
}claude_desktop_config.json · Customize › Connectors › Add custom connector
{
"mcpServers": {
"base-de-conhecimento": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://api.mcp.ai/p_kb"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"base-de-conhecimento": {
"url": "https://api.mcp.ai/p_kb"
}
}
}