Alpaca Trading
This MCP server provides complete Alpaca trading platform integration, enabling AI assistants to manage stock and options trading accounts through paper and live trading environments. Built using Python with the alpaca-py SDK and FastMCP framework, it offers account monitoring with real-time balance and position tracking, comprehensive order management supporting market, limit, stop, stop-limit, and trailing stop orders, historical and real-time market data retrieval including quotes, bars, and trade history, position management with partial and full closure capabilities, watchlist creation and management, and market calendar information with corporate action announcements. The implementation includes proper error handling for API rate limits and trading restrictions, environment variable configuration for secure credential management, and support for both stock and options trading workflows, making it valuable for algorithmic trading development, portfolio management automation, and financial analysis workflows that require programmatic access to brokerage account functionality.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- finance
- Source
- PulseMCP
- Repository
- github.com/alpacahq/alpaca-mcp-server
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Alpaca Trading from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.