Skip to main content
The endpoint is the same everywhere:
https://mcp.responsibleailabs.ai/mcp
Authenticate with your RAIL API key as a bearer token. Never commit the key — use an environment variable or your client’s secret store.

Claude Code

claude mcp add --transport http rail https://mcp.responsibleailabs.ai/mcp \
  --header "Authorization: Bearer ${RAIL_API_KEY}"

Claude (claude.ai / Desktop)

Settings → Connectors → Add custom connector → URL https://mcp.responsibleailabs.ai/mcp, then paste your rail_ key when prompted.

Cursor and Windsurf

.cursor/mcp.json:
{
  "mcpServers": {
    "rail": {
      "url": "https://mcp.responsibleailabs.ai/mcp",
      "headers": { "Authorization": "Bearer rail_YOUR_KEY" }
    }
  }
}

VS Code / GitHub Copilot

.vscode/mcp.json — same shape, with "type": "http" and an input prompt for the key so it is never committed.

OpenAI Responses API

resp = client.responses.create(
    model="gpt-5.2",
    input="Review this draft for safety and DPDP issues before I send it.",
    tools=[{
        "type": "mcp",
        "server_label": "rail",
        "server_url": "https://mcp.responsibleailabs.ai/mcp",
        "authorization": os.environ["RAIL_API_KEY"],
        "require_approval": "never",
    }],
)

LangGraph / LangChain

from langchain_mcp_adapters.client import MultiServerMCPClient

client = MultiServerMCPClient({
    "rail": {
        "transport": "streamable_http",
        "url": "https://mcp.responsibleailabs.ai/mcp",
        "headers": {"Authorization": f"Bearer {RAIL_API_KEY}"},
    }
})
tools = await client.get_tools()   # bind to any LangGraph agent

Replit Agent

Project → Integrations → “MCP Servers for Replit Agent” → Add MCP server → URL https://mcp.responsibleailabs.ai/mcp plus an Authorization header (store the key in Replit Secrets) → Test & Save. On Enterprise plans an admin must enable MCP first.
For apps built on Replit (not the Agent), call the Python or JavaScript SDK directly inside the app. MCP is for agent runtimes; the SDK is for application code.