SNCF for AI agents
SNCF's passenger-information API covers French train schedules, station boards, journey planning, and live service status for the national rail network. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.
What agents do in SNCF.
Check a train's live status
Get the current service status for a line to confirm whether a scheduled train is delayed.
Look up a station's departure board
Get a station's board to see upcoming departures before recommending a connection to a traveler.
Plan a journey between two stations
Plan a journey between two stations, returning route and timing options for a trip.
9 SNCF actions, graded by risk.
Every SNCF action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
8Look things up. Allowed by default.
- sncf.list_coverageGet SNCF Coverage
- sncf.search_placesSearch Places
- sncf.get_station_boardGet Station Board
- sncf.find_nearby_placesFind Nearby Places
- sncf.get_service_statusGet Service Status
- sncf.get_transport_objectGet Transport Object
- sncf.list_transport_objectsList Transport Objects
- sncf.search_transport_objectsSearch Transport Objects
write
1Create and change things. Allow, or ask the user first.
- sncf.plan_journeyPlan Journey
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
SNCF in three steps.
- 01Your users connect SNCFThey add their SNCF api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “plan Journey” can wait for the user to approve.
- 03Any agent can actYour agent calls SNCF through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('sncf', { read: 'allow', write: 'ask', // plan_journey destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How SNCF connects.
Users add their SNCF api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
The same SNCF connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →
- AUTH
- API key
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use SNCF from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
SNCF and Arc0, answered.
Can I use SNCF with Claude, ChatGPT or Cursor?
Yes. Connect SNCF to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the SNCF actions you allow.
How do users connect SNCF?
Users add their SNCF api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
Which SNCF actions can my agent take?
9 in total: 8 read, 1 write and 0 destructive, such as “plan Journey”. Your policies decide which of them each agent may call.
Can I make my agent read-only in SNCF?
Yes. Allow read actions and deny writes in the SNCF policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call SNCF too?
Yes. The same SNCF connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug SNCF into your agent.
Your users connect SNCF once, under your brand. Your agent gets 9 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan