AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
API Integration/
alpaca-mcp-server
alpaca-mcp-server logo

alpaca-mcp-server

Active·★ 1.0k·MIT·Updated 2026-10-27
★ Essential★ Trending

This is the MCP server for Alpaca's Trading API, published by AlpacaHQ. It lets assistants such as Claude, Cursor and VS Code run natural-language trading operations across stocks, options and crypto. The README lists market data (quotes, trades, bars, option Greeks and implied volatility), account and portfolio views, orders (market, limit, stop, stop-limit and trailing-stop), options including multi-leg strategies, crypto orders, position management, news, market status and watchlists.

Version 2 is a complete rewrite built with FastMCP and OpenAPI, and the README says none of the V1 tools exist in V2, so you should treat it as a new server and reconfigure your client. Configuration is now only environment variables in the MCP client config, such as `ALPACA_API_KEY` and `ALPACA_SECRET_KEY`. An `ALPACA_TOOLSETS` variable filters which tool groups the server exposes. `ALPACA_PAPER_TRADE` defaults to `true`, and the README tells you to set it to `false` for live trading, so a new setup starts on the paper account.

Setup needs Python 3.10+, `uv`, Alpaca API keys from a free paper-trading account, and an MCP client; the server runs with `uvx alpaca-mcp-server`. It is MIT licensed and the last push was 2026-10-12. The README ends with long regulatory disclosures: the content is not investment advice, past performance does not guarantee future results, and securities and crypto services are provided by separate Alpaca entities. This review is based on the README and repository data; we have not run it ourselves.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool. Data as of 2026-10-22.

License
MIT
Latest release
v2.4.0 · 2026-10-12
Last commit
2026-10-12
Contributors
18
Forks
348
Open issues and PRs
27
First published
2025-06-03
PyPI package
alpaca-mcp-server 2.4.0 · 12,769 downloads last week

Source: GitHub, npm and PyPI public APIs.

#Trading API#AI Assistants#Financial Markets#Natural Language Processing#Model Context Protocol#Stock Trading#Crypto Trading#Options Trading
$ Install
$ uvx alpaca-mcp-server
↗ Visit site★ GitHub
01

Features

01Market Data: Real-time and historical data for stocks, crypto, and options.
02Order Management: Place various order types for stocks, crypto, and options.
03Account Management: View balances, buying power, and portfolio history.
04Options Trading: Advanced options capabilities including contract search and strategy placement.
05Watchlist Management: Create, update, and manage asset watchlists.
02

Why choose it

+Covers stocks, options (including multi-leg) and crypto: data, orders, positions, news and watchlists
+Paper trading is the default, so you can test with no real money
+`ALPACA_TOOLSETS` limits which tool groups an assistant can see
+Official server from Alpaca, MIT licensed, run with `uvx`
03

Trade-offs

!With `ALPACA_PAPER_TRADE=false` an assistant can place real orders, so keep live mode off unless you add limits and confirmations
!V2 breaks V1: tool names and parameters changed, so old prompts, rules and configs need updating
!A model can misread a prompt and trade the wrong size or symbol, and orders can be hard to undo
!Account data and positions are sent to the model provider; the README stresses it is not investment advice
05

Maintenance check

ActiveChecked: 2026-10-24
Last commit
2026-10-23
Commits, last 90 days
13
Releases, last 90 days
2
Latest release
v2.4.0 (2026-10-12)
Open issues
27
Recent issues with at least one comment
4/12
Commits per week, last 12 weeks
Commits per week, last 12 weeks: 1, 1, 0, 2, 2, 0, 3, 1, 0, 0, 1, 1

Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

Most discussed open issues

  • #14 mcp error on Claude desktop & error on MCP Client19 comments · 2025-07-08
  • #12 mcp error with gemini cli8 comments · 2025-06-26
  • #32 Installation error: No module named 'alpaca_mcp_server'5 comments · 2025-11-20
  • #16 MCP Server Auth with live trading5 comments · 2025-07-30
  • #75 Claude4 comments · 2026-04-30

Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.

04

Who it fits

Pick it if
  • You already have an Alpaca account and want an assistant to read quotes, positions and news and place orders on stocks, options and crypto.
  • You want to start safely: paper trading is the default.
  • You want to limit what the assistant sees with `ALPACA_TOOLSETS`.
Look elsewhere if
  • You trade through a different broker: this server is for Alpaca's API only.
  • You have prompts or configs built on V1: V2 is a rewrite and none of the V1 tools exist.
  • You would switch on live trading without limits and confirmations: a model can misread a prompt and orders can be hard to undo.
06

How it differs

QuantDinger logovs QuantDinger★ 13.2k

QuantDinger is a self-hosted platform from research to backtest to execution across several brokers. Alpaca's server is a thin tool layer over one broker's API.

Full comparison →
07

Compatibility

Python
Runtime
Verified via docs
uv
Package Runner
Verified via docs
Claude Desktop
MCP Client
Verified via docs
Cursor
MCP Client
Verified via docs
VS Code
MCP Client
Verified via docs
PyCharm
MCP Client
Verified via docs
08

Quick start

1
$ uvx alpaca-mcp-server
09

Use cases

↳Execute natural language trading commands for stocks, options, and crypto.
↳Query real-time and historical market data for various assets.
↳Manage personal trading accounts, including balances, positions, and orders.
↳Create and update watchlists for monitoring specific securities.
↳Automate complex trading strategies by combining multiple operations.
10

Alternatives

⚡Top VS:
VSQuantDinger★13.2k→VSmcp★170→VSFigma-Context-MCP★16.1k→VSmcp★9.8k→
QuantDinger logo
QuantDinger★ 13.2k
AI quantitative trading platform for crypto, stocks, and forex with backtesting, live trading, market data, and multi-agent research.vibe-trading ,trading-agents,ai-trader,ai-trading
VSCompare→
mcp logo
mcp★ 170
🤖 Taskade MCP · Official MCP server and OpenAPI to MCP codegen. Build AI agent tools from any OpenAPI API and connect to Claude, Cursor, and more.
VSCompare→
Figma-Context-MCP logo
Figma-Context-MCP★ 16.1k
MCP server to provide Figma layout information to AI coding agents like Cursor
VSCompare→
mcp logo
mcp★ 9.8k
AWS MCP Servers — helping you get the most out of AWS, wherever you use MCP.
VSCompare→
google_workspace_mcp logo
google_workspace_mcp★ 3.4k
Control Gmail, Google Calendar, Docs, Sheets, Slides, Chat, Forms, Tasks, Search & Drive with AI - Comprehensive Google Workspace / G Suite MCP Server
VSCompare→
advanced-homeassistant-mcp logo
advanced-homeassistant-mcp★ 58
An advanced MCP server for Home Assistant. 🔋 Batteries included.
VSCompare→
ext-apps logo
ext-apps★ 3.0k
Official repo for spec & SDK of MCP Apps protocol - standard for UIs embedded AI chatbots, served by MCP servers
VSCompare→
mcp-server-kubernetes logo
mcp-server-kubernetes★ 1.6k
MCP Server for kubernetes management commands
VSCompare→
See all alternatives →

Featured in these lists

  • Open-Source AI Trading and Finance Tools

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs05Maintenance check04Who it fits06How it differs07Compatibility08Quick start09Use cases10Alternatives
alpacahq /
alpaca-mcp-server
↗

Official MIT MCP server for Alpaca's trading API: quotes, options, crypto, positions and orders, with paper trading on by default

1.0k348MIT
Last commit1d ago
StatusActive
CategoryAPI Integration
Contributors18
Latest releasev2.4.0
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.