trademind-unified-mcp
Enables unified access to portfolio management, market data, risk analysis, trade records, compliance checks, and Slack notifications through a single MCP server.
README
trademind-unified-mcp
TradeMind AI's 6 MCP servers merged into one standalone server / one repo:
| Domain | Tools |
|---|---|
| Portfolio | get_portfolio_snapshot, get_allocation_breakdown, get_pnl_history |
| Market Data | get_market_snapshot, get_price_history, get_volatility_metrics |
| Risk Engine | calculate_var, calculate_sharpe, get_exposure_analysis |
| Trade Records | get_trade_history, get_execution_details, reconcile_trades |
| Compliance DB | check_restrictions, get_audit_trail, validate_compliance |
| Slack | send_notification, get_channel_history, create_thread |
18 tools, 1 process, 1 port.
Why this exists
The original 6 repos (portfolio-mcp, market-data-mcp, risk-engine-mcp,
trade-records-mcp, compliance-db-mcp, slack-mcp) each ran as their own
server. This repo copies each module's tool classes in locally (no npm
workspace/package dependency on the rest of the trademind monorepo), so it
can be pushed as one standalone GitHub repo and imported as one
NitroStack app.
No business logic was changed — this is a structural merge only. All responses are currently mock/simulated data unless the optional live-data env vars below are set (same behavior as the original repos).
Run locally
npm install
cp .env.example .env
npm run dev
Server starts on http://localhost:3150 (configurable via UNIFIED_MCP_PORT).
GET /health reports status and the 18 registered tools.
Deploy to NitroStack / NitroCloud
- Push this folder as its own GitHub repo.
- In NitroCloud → Apps → Create App, import this repo.
- Set env vars from
.env.examplein the app's settings (all are optional — tools fall back to simulated data if unset).
Environment variables
See .env.example. All are optional:
UNIFIED_MCP_PORT— defaults to 3150CONTEXT_ENGINE_URL— if set, tool results are also written there (fire-and-forget)POLYGON_API_KEY/TWELVEDATA_API_KEY— enables live market data inmarket-datatoolsSLACK_BOT_TOKEN— enables live Slack posting insend_notification
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.