// SCAN REPORT

SubwayInfo NYC

22 tools. 1 can modify or destroy data without limits.

1 write tool that can modify data. Rate limits recommended.

Last updated:

1 can modify or destroy data
21 read-only
22 tools total
// TOOL MAP
Read (21) Write / Execute (1) Destructive / Financial (0)
// WHAT CAN GO WRONG
✕

Write operations (mta_plan_trip) 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 SubwayInfo NYC. 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 @ckbk/subwayinfo-nyc
Scans every tool. Generates a policy. Starts enforcing.
Works with Claude Code · Cursor · Claude Desktop · Windsurf · any MCP client
// RECOMMENDED RULES
Rate limit write operations
mta_plan_trip:
  rules:
    - rate_limit: 30/hour

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
bike_get_availability_summary:
  rules:
    - rate_limit: 60/minute

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

// ALL 22 SUBWAYINFO NYC TOOLS
WRITE 1 tools
Write mta_plan_trip
READ 21 tools
Read bike_get_availability_summary Read bike_get_station_status Read bike_search_stations Read bus_get_arrivals Read bus_get_route_info Read bus_list_alerts Read bus_search_stops Read ferry_get_arrivals Read ferry_get_routes Read ferry_list_alerts Read ferry_search_landings Read mta_get_arrivals Read mta_get_line_status Read mta_get_station_info Read mta_list_alerts Read mta_search_stations Read rail_get_departures Read rail_get_station_info Read rail_list_alerts Read rail_search_stations Read transit_ask
// FAQ
How do I prevent bulk modifications through SubwayInfo NYC? +

The SubwayInfo NYC server has 1 write tools including mta_plan_trip. 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 SubwayInfo NYC MCP server expose? +

22 tools across 2 categories: Read, Write. 21 are read-only. 1 can modify, create, or delete data.

How do I add Intercept to my SubwayInfo NYC setup? +

One line change. Instead of running the SubwayInfo NYC server directly, prefix it with Intercept: intercept -c ckbk-subwayinfo-nyc.yaml -- npx -y @ckbk/subwayinfo-nyc. Download a pre-built policy from policylayer.com/policies/ckbk-subwayinfo-nyc and adjust the limits to match your use case.

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.
// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.