Atlas

Created By
finmanagerai5 days ago
Connect AI agents to Atlas MCP for live market data, options analytics, strategy workflows, and 50+ broker-aware trading capabilities.
Overview

Atlas MCP Server animated headline

Connect AI agents to Atlas so they can read markets, build workflows, send alerts, and place broker orders with your approval.

Install · Why · What it can do · Examples · Tools · FAQ · Safety

MCP AI Agents Broker Orders Options Alerts


Atlas MCP Server

Stop jumping between charts, brokers, alerts, spreadsheets, and chat apps.

Atlas MCP lets AI agents help with investing tasks in one place:

Ask Agent → Analyze Market → Review Plan → Stage Orders → Automate Workflow → Send Alerts
Atlas MCP workflow

Atlas MCP gives agents a safe way to:

  • Read live market data
  • Analyze stocks and options
  • Check broker accounts
  • Stage single or multiple orders
  • Send alerts to Discord, SMS, Telegram, and chat apps
  • Create repeatable investing workflows

It works with agent tools like:

  • OpenClaw
  • Claude Desktop
  • Cursor
  • Cline
  • ChatGPT-compatible MCP clients
  • Custom agents

Install

Atlas MCP is a hosted, remote MCP server. There's nothing to compile or self-host — your agent connects to https://atlasmcp.finmanagerai.com/mcp over streamable HTTP, and authenticates with your personal Atlas API key.

1. Get your Atlas API key

  1. Go to https://www.mind-vest.io/atlas and sign in (or create an account).
  2. Open the DashboardAPI Keys section.
  3. Click Generate key and copy the value. Treat it like a password.

2. Add Atlas to your MCP client

Claude Desktop / Claude Code / Cursor / Cline / any MCP client that reads mcp.json:

{
  "mcpServers": {
    "atlas": {
      "type": "streamable-http",
      "url": "https://atlasmcp.finmanagerai.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_ATLAS_API_KEY"
      }
    }
  }
}

Claude Code one-liner:

claude mcp add --transport http atlas https://atlasmcp.finmanagerai.com/mcp \
  --header "Authorization: Bearer YOUR_ATLAS_API_KEY"

Anything that follows the MCP registry:

io.github.finmanagerai/atlas-mcp-server

Then restart your client. Ask the agent to "show me an SPY quote" — if a quote comes back, you're connected.

Per-client install recipes

Each recipe covers config path, install command, env vars, test prompt, and troubleshooting:

Letting an AI agent install it for you

Drop SKILL.md into your agent's skills/instructions and it will pick the right recipe, plug in the user's key, and run the smoke test on its own.

More

Heads-up: This repo intentionally contains only the public configuration needed to install and discover Atlas MCP. The server implementation, broker connectors, and proprietary data pipelines are not open-sourced.


Why Atlas MCP?

Most agents can explain the market.

But they usually cannot do the useful parts together:

  • Check live stock data
  • Read options chains
  • Find high-volume or high-open-interest contracts
  • Check account balances and positions
  • Prepare trades across brokers
  • Stage multiple orders at once
  • Automate alerts and workflows
  • Send updates to Discord, SMS, Telegram, or chat apps
  • Keep you in control before anything is submitted

Atlas MCP closes that gap.

It helps agents move from:

"Here is what I think."

to:

"Here is the market data, here is the plan, here are the orders, review before sending."

What it can do

Market research

  • Get live stock quotes
  • Pull price history
  • Check earnings dates
  • Review analyst ratings
  • Read company financials
  • Compare related stocks

Options research

  • Read options chains
  • Find top-volume contracts
  • Find top-open-interest contracts
  • Review Greeks
  • Analyze Gamma, Delta, Vanna, and Theta exposure

Broker actions

  • Connect to supported brokers
  • Check balances and positions
  • Preview stock orders
  • Preview options orders
  • Stage multiple orders at once
  • Submit approved orders

Supported brokers can include:

  • Alpaca
  • Webull
  • Tradier
  • Public
  • 20+ popular brokers depending on your connected broker setup

Robinhood and Fidelity are not supported for trading features.

Alerts and workflows

  • Send trade alerts to Discord
  • Send SMS alerts
  • Send Telegram alerts
  • Create watchlist scans
  • Create price-trigger workflows
  • Automate daily or weekly market checks
  • Deliver updates to chat apps

Example prompts

Show me the top-volume SPY options contracts today.
Check my buying power and preview buying 5 NVDA and 5 AMD.
If QQQ breaks above 430, send me a Discord alert and stage a trade for review.
Scan my watchlist every morning and text me the best setups.
Preview multiple orders across my connected broker account. Do not submit until I approve.

Supported tools

Atlas MCP can expose tools for:

  • Stocks
  • Options
  • Greeks
  • Charts
  • Broker accounts
  • Order previews
  • Order placement
  • Trading triggers
  • Workflow automation
  • Strategy notes
  • Discord alerts
  • SMS alerts
  • Telegram alerts

FAQ

Is Atlas MCP a trading bot?

No. Atlas MCP is a tool layer for AI agents. It helps agents read data, create workflows, preview orders, and send alerts. You stay in control.

Can it place real orders?

Yes, when broker connections and permissions are enabled. The safest flow is preview first, then submit only after approval.

Can it submit multiple orders at once?

Yes. Atlas MCP can stage multiple orders together, so you do not have to enter each trade one by one.

Can it trade options?

Yes, when your broker connection supports options trading. Atlas MCP can help with options chains, contract lookup, Greeks, and order previews.

Does it support Discord, SMS, and Telegram?

Yes. Workflows can send alerts, summaries, and trade updates to Discord, SMS, Telegram, and chat apps.

Does it support Webull, Alpaca, Tradier, and Public?

Yes. Atlas MCP can support broker workflows through Alpaca, Webull, Tradier, Public, and 20+ popular brokers depending on your enabled broker connection.

Does it support Robinhood or Fidelity trading?

No. Trading features are not available for Robinhood and Fidelity.

Is this financial advice?

No. Atlas MCP is software for market research and workflow automation. It does not give financial advice.


Safety

This project is for education, research, and workflow automation only.

Trading stocks, options, and other assets is risky. You are responsible for your own trades, broker connections, order approvals, automation settings, and results.

Always review orders before submitting them.

Server Config

{
  "mcpServers": {
    "atlas": {
      "url": "https://atlasmcp.finmanagerai.com/mcp",
      "transport": "streamable-http",
      "headers": {
        "Authorization": "Bearer YOUR_ATLAS_API_KEY"
      }
    }
  }
}
Project Info
Created At
5 days ago
Updated At
3 days ago
Author Name
finmanagerai
Star
-
Language
-
License
-
Category
Tags

Recommend Servers

View All
Tavily Mcp
@tavily-ai

JavaScript
a year ago
Polymarket Intel
@aemery13

An MCP server and REST API that classifies Polymarket wallets as human or bot, scores their trading edge from 0–10, and streams their current open positions. Built for AI agents on copy-trading and signal-following stacks. # Use it from any MCP client (Claude Desktop, Cursor, etc.) pip install polymarket-intel-mcp polymarket-intel-mcp # Or call the hosted REST API directly curl https://polymarket-intel-production.up.railway.app/wallet/0xf1528f12e645462c344799b62b1b421a6a4c64aa How this fits with other Polymarket MCP servers There are several MCP servers covering Polymarket, each at a different layer: Server What it does When to use it polymarket-intel (this) Wallet intelligence — classify human vs bot, score trading edge, read open positions Deciding whose signals to follow graph-polymarket-mcp Market data via The Graph subgraphs (20 tools, 8 subgraphs) Reading raw on-chain market data whitmorelabs/polymarket-mcp Slippage, liquidity, arbitrage, price feeds Pricing your own trades joinQuantish/polymarket Self-hosted trading agent Running an autonomous bot These complement each other. A copy-trading agent would use polymarket-intel to filter wallets worth following, then graph-polymarket-mcp to read the markets those wallets are betting on, then whitmorelabs/polymarket-mcp to size its own entries. What it answers "Is this trader a human or a bot?" — score_polymarket_wallet(wallet_address) → returns classification ∈ {human, bot, insufficient_data} plus a confidence score and reason codes. "Do they actually have an edge?" — edge_score from 0–10, gated on net realised PnL so distributed-but-losing wallets don't get false positives. "What are they betting on right now?" — get_open_positions(wallet_address) returns live positions sorted by size, refreshed every 30s. "How has their edge changed over time?" — /wallet/{address}/history returns the score time series from the daily snapshots. Why this exists The Polymarket leaderboard is misleading. It includes unrealised PnL marked-to-current-price, so the names at the top are dominated by bots running structural arb plus a few wallets sitting on huge open positions that may never resolve in their favour. Agents that copy-trade naively from the leaderboard get burned. This service runs every leaderboard wallet through behavioural fingerprinting (focus ratio, holding period, timing regularity, category concentration) plus PnL reconstruction from raw activity, and only surfaces traders that look like genuine humans with a real edge. The dataset grows more valuable over time — every day the snapshot job runs, historical signals accumulate. Wallets that have been consistently above edge 7 for 90 days are a stronger signal than any single point-in-time score. Distributed as both a REST API and an MCP server Surface Use case Setup MCP server Agent that needs tool-style access pip install polymarket-intel-mcp REST API Custom HTTP integration, dashboards curl https://polymarket-intel-production.up.railway.app/... Hosted MCP Agent on any MCP-compatible client Add https://polymarket-intel-production.up.railway.app/mcp to client config Architecture ┌──────────────────────────────────────────────┐ │ core/ │ │ client.py — Polymarket data API client │ │ signals.py — pure signal calculators │ │ scorer.py — classifier + edge score │ │ models.py — Pydantic response schemas │ ├──────────────────────────────────────────────┤ │ db/ │ │ schema.sql — Postgres tables + indexes │ │ repository.py — Repository protocol + │ │ InMemoryRepository │ │ supabase_repo.py — Supabase impl │ │ converters.py — ScoreResult ↔ records │ ├──────────────────────────────────────────────┤ │ api/main.py — FastAPI HTTP server │ │ mcp_server/ — MCP server (stdio) │ │ scripts/ │ │ analyze_wallet.py — CLI │ │ snapshot_job.py — daily cron entry │ │ tests/ │ └──────────────────────────────────────────────┘ Core has no idea persistence exists. The API and snapshot job depend on the Repository protocol — Supabase in production, in-memory in tests and when env vars are unset. This is what makes the suite run without a database and what lets you swap Supabase for Neon, RDS, or anything else later by adding one file.

12 hours ago
Datagrout

2 days ago
Coinrebate

a day ago