Atlas
About
Connect AI agents to Atlas MCP for live market data, options analytics, strategy workflows, and 50+ broker-aware trading capabilities .
Details
- Author
- finmanagerai
- Downloads
- 277
- Categories
- Search
Jump to
- Live stock quotes and price history
- Options chains with Greeks and volume
- Broker account balances and positions
- Order preview and staged multi‑order placement
- Alerts via Discord, SMS, and Telegram
- Workflow automation for daily or triggered checks
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
AtlasCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Get your personal API key from Mind-Vest's Atlas dashboard, then add the server to any MCP client using the streamable HTTP endpoint https://atlasmcp.finmanagerai.com/mcp with a Bearer token in the Authorization header. Detailed install recipes are provided for Claude Desktop, Claude Code, Cursor, Windsurf, OpenAI Codex CLI, OpenClaw, and Docker.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"atlas": {
"atlas": {
"url": "https://atlasmcp.finmanagerai.com/mcp",
"transport": "streamable-http",
"headers": {
"Authorization": "Bearer YOUR_ATLAS_API_KEY"
}
}
}
}
}
McpServers
{
"atlas": {
"url": "https://atlasmcp.finmanagerai.com/mcp",
"transport": "streamable-http",
"headers": {
"Authorization": "Bearer YOUR_ATLAS_API_KEY"
}
}
}
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 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 Dashboard → API 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:
- Claude Desktop
- Claude Code
- Cursor
- Windsurf
- OpenAI Codex CLI
- OpenClaw
- Docker (stdio bridge)
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
- Tool catalog — every tool, with read/write classification
- Security & permissions — auth model, rate limits, what Atlas can and can't do
- Example prompts
- CI smoke test + examples/smoke-test.sh
- Changelog
> 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.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.

