// SCAN REPORT

Alpaca Trading Integration

35 tools. 9 can modify or destroy data without limits.

3 destructive tools with no built-in limits. Policy required.

Last updated: 5 Apr 2026

9 can modify or destroy data

26 read-only

35 tools total

// TOOL MAP

Read (26) Write / Execute (6) Destructive / Financial (3)

// WHAT CAN GO WRONG

Destructive tools (alpaca-cancelOrder, alpaca-cancelOrders, alpaca-deleteWatchlist) permanently delete resources. There is no undo. An agent calling these in a retry loop causes irreversible damage.

Write operations (alpaca-closePosition, alpaca-closePositions, alpaca-createOrder) modify state. Without rate limits, an agent can make hundreds of changes in seconds — faster than any human can review or revert.

One command. Full control.

Intercept sits between your agent and Alpaca Trading Integration. Every tool call checked against your policy before it executes — so your agent can do its job without breaking things.

npx -y @policylayer/intercept scan -- npx -y @wlu03/alpaca-mcp

Scans every tool. Generates a policy. Starts enforcing.

Works with Claude Code · Cursor · Claude Desktop · Windsurf · any MCP client

// RECOMMENDED RULES

Deny destructive operations

alpaca-cancelOrder:
  rules:
    - action: deny

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

alpaca-closePosition:
  rules:
    - rate_limit: 30/hour

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

alpaca-exerciseOption:
  rules:
    - rate_limit: 60/minute

Controls API costs and prevents retry loops from exhausting upstream rate limits.

// ALL 35 ALPACA TRADING INTEGRATION TOOLS

DESTRUCTIVE 3 tools

Destructive alpaca-cancelOrder Destructive alpaca-cancelOrders Destructive alpaca-deleteWatchlist

WRITE 6 tools

Write alpaca-closePosition Write alpaca-closePositions Write alpaca-createOrder Write alpaca-createWatchlist Write alpaca-replaceOrder Write alpaca-updateWatchlist

// FAQ

Can an AI agent delete data through the Alpaca Trading Integration MCP server? +

Yes. The Alpaca Trading Integration server exposes 3 destructive tools including alpaca-cancelOrder, alpaca-cancelOrders, alpaca-deleteWatchlist. These permanently remove resources with no undo. Intercept blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Alpaca Trading Integration? +

The Alpaca Trading Integration server has 6 write tools including alpaca-closePosition, alpaca-closePositions, alpaca-createOrder. Set rate limits in your policy file -- for example, rate_limit: 10/hour prevents an agent from making more than 10 modifications per hour. Intercept enforces this at the transport layer.

How many tools does the Alpaca Trading Integration MCP server expose? +

35 tools across 3 categories: Destructive, Read, Write. 26 are read-only. 9 can modify, create, or delete data.

How do I add Intercept to my Alpaca Trading Integration setup? +

One line change. Instead of running the Alpaca Trading Integration server directly, prefix it with Intercept: intercept -c wlu03-alpaca-mcp.yaml -- npx -y @wlu03/alpaca-mcp. Download a pre-built policy from policylayer.com/policies/wlu03-alpaca-mcp and adjust the limits to match your use case.

// RELATED SERVERS

Other MCP servers with similar tools.

Starter policies available for each. Same risk classification, same one-command setup.

policylayer/intercept

Control every MCP tool call
your agent makes.

Set budgets, approvals, and hard limits across MCP servers.

npx -y @policylayer/intercept init

Protect your agent in 30 seconds. Scans your MCP config and generates enforcement policies for every server.

Alpaca Trading Integration

One command. Full control.

Other MCP servers with similar tools.

Control every MCP tool call your agent makes.

Control every MCP tool call
your agent makes.