Research-grade investment decision engine for AI agents: isolated multi-agent committee, auditable verdicts, backtests with lookahead protection, published negative results
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add openinvest -- uvx openinvest~/.codex/config.toml
[mcp_servers.openinvest]
command = "uvx"
args = ["openinvest"]
# codex mcp add openinvest -- uvx openinvest~/.cursor/mcp.json
{
"mcpServers": {
"openinvest": {
"command": "uvx",
"args": [
"openinvest"
]
}
}
}.vscode/mcp.json
{
"servers": {
"openinvest": {
"type": "stdio",
"command": "uvx",
"args": [
"openinvest"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"openinvest": {
"command": "uvx",
"args": [
"openinvest"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"openinvest": {
"command": "uvx",
"args": [
"openinvest"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"openinvest": {
"command": "uvx",
"args": [
"openinvest"
]
}
}
}