AI & Machine Learning
nexustrade.io
An AI-native algorithmic trading platform for building, validating, and operating trading systems with Aurora or real community trading bots.
ENDPOINT 1
https://nexustrade.io/api/mcp
MCP server metadata
- Name
- NexusTrade
- Version
- 1.0.0
NexusTrade MCP — portfolio authoring Prefer structured create_portfolio / build_portfolio (zero LLM cost). Validate drafts with build_portfolio before create_portfolio. Custom data sources: none yet. Create one with run_compute (pass name and point_kind to promote its signal output directly), or use dataset_to_indicator with a saved dataset; then reference customIndicatorId in create_portfolio.
Known tools 24
create_agent⚠ COSTS LLM CREDITS on the NexusTrade account — spins up an Aurora agent via Router V5 classification + ReAct execution loops, billed per token.
Inferred read-onlyget_agent_trajectoryAurora agent surface (no LLM cost on this call — pure DB read).
Inferred read-onlyquery_backtest_historyReturn a time series of {time, value, cash, positionValue, comparisonValue, reservedCollateral} per tick for a completed backtest.
Inferred read-onlyquery_backtest_statusReturn the parent backtest document's status, error, interval, timestamps, elapsed time, and completed statistics without reading history/events.
Inferred read-onlycreate_portfolio_variantDeep-copy a source chat or deployed portfolio into a new ChatPortfolio with fresh strategy IDs.
Inferred read-onlyapprove_agent_plan⚠ INDIRECTLY COSTS LLM CREDITS — approving the plan unfreezes the agent which then runs more planning + execution LLM calls.
Inferred read-onlyreject_agent_actionAurora agent surface (minimal LLM cost — state transition, no re-planning).
Inferred read-onlysend_agent_message⚠ COSTS LLM CREDITS — re-runs the Aurora planner LLM after appending the user's follow-up.
Inferred read-onlyfetch_portfoliosList or search your portfolios with lightweight metadata (strategy id + name).
Inferred read-onlyget_portfolioFetch one portfolio with full strategy objects (condition, action, indicators), positions, and spread-grouped holdings.
Inferred read-onlybacktest_portfolioSubmit an asynchronous historical backtest for a portfolio over a date range.
Inferred read-onlysearch_public_portfoliosSearch and browse publicly shared portfolios from other NexusTrade users, sorted by performance metrics.
Inferred read-onlyupdate_portfolioDeploy, undeploy, rename, delete, add/remove/replace strategies, or set deployment frequency on portfolios.
Potential side effectsclone_strategies_to_portfolioReplace a deployed (paper/live) portfolio's entire strategy set with deep copies of a source portfolio's strategy objects (by reference, not YAML).
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.nexustrade]
url = "https://nexustrade.io/api/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"nexustrade": {
"type": "http",
"url": "https://nexustrade.io/api/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: nexustrade
Remote MCP URL: https://nexustrade.io/api/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"nexustrade": {
"url": "https://nexustrade.io/api/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"nexustrade": {
"type": "http",
"url": "https://nexustrade.io/api/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "nexustrade",
"transport": "streamable-http",
"url": "https://nexustrade.io/api/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Trust Data Available
BuiltWith Trust API v2 evidence for nexustrade.io was fetched 2026-08-23T13:52:06.862Z and is being refreshed.
nexustrade.io is assessed as Trusted: Domain has an established technology history spanning over a year.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.