// SCAN REPORT

Railway MCP Server

38 tools. 23 can modify or destroy data without limits.

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

Last updated: 20 Apr 2026

23 can modify or destroy data

15 read-only

38 tools total

// TOOL MAP

Read (15) Write / Execute (17) Destructive / Financial (6)

// WHAT CAN GO WRONG

Destructive tools (domain_delete, project_delete, service_delete) permanently delete resources. There is no undo. An agent calling these in a retry loop causes irreversible damage.

Write operations (configure_api_token, domain_create, domain_update) modify state. Without rate limits, an agent can make hundreds of changes in seconds — faster than any human can review or revert.

Execute tools (deployment_logs, deployment_trigger, service_restart) trigger processes with side effects. Builds, notifications, workflows — all fired without throttling.

One command. Full control.

Intercept sits between your agent and Railway MCP Server. 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 @jason-tan-swe/railway-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

domain_delete:
  rules:
    - action: deny

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

Rate limit write operations

configure_api_token:
  rules:
    - rate_limit: 30/hour

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

database_list_types:
  rules:
    - rate_limit: 60/minute

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

// ALL 38 RAILWAY MCP SERVER TOOLS

DESTRUCTIVE 6 tools

Destructive domain_delete Destructive project_delete Destructive service_delete Destructive tcp_proxy_delete Destructive variable_delete Destructive volume_delete

EXECUTE 4 tools

Execute deployment_logs Execute deployment_trigger Execute service_restart Execute template_deploy

WRITE 13 tools

Write configure_api_token Write domain_create Write domain_update Write project_create Write service_create_from_image Write service_create_from_repo Write service_update Write tcp_proxy_create Write variable_bulk_set Write variable_copy Write variable_set Write volume_create Write volume_update

READ 15 tools

Read database_list_types Read deployment_list Read deployment_status Read domain_check Read domain_list Read list_service_variables Read project_environments Read project_info Read project_list Read service_info Read service_list Read tcp_proxy_list Read template_get_workflow_status Read template_list Read volume_list

// FAQ

Can an AI agent delete data through the Railway MCP Server MCP server? +

Yes. The Railway MCP Server server exposes 6 destructive tools including domain_delete, project_delete, service_delete. 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 Railway MCP Server? +

The Railway MCP Server server has 13 write tools including configure_api_token, domain_create, domain_update. 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 Railway MCP Server MCP server expose? +

38 tools across 4 categories: Destructive, Execute, Read, Write. 15 are read-only. 23 can modify, create, or delete data.

How do I add Intercept to my Railway MCP Server setup? +

One line change. Instead of running the Railway MCP Server server directly, prefix it with Intercept: intercept -c jason-tan-swe-railway-mcp.yaml -- npx -y @jason-tan-swe/railway-mcp. Download a pre-built policy from policylayer.com/policies/jason-tan-swe-railway-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.

Railway MCP Server

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.