idfm-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| IDFM_API_KEY | Yes | Your PRIM API key from prim.iledefrance-mobilites.fr. Required for the server to authenticate with the Île-de-France Mobilités PRIM API. Can be provided via the MCP server env configuration or a .env file. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Real-time public transport for Paris and Île-de-France (Metro, RER, Transilien, Tram, Bus). Typical flow: search_stop to get a station ID, then next_departures with that ID. plan_journey and traffic_disruptions accept plain names directly. All times are Europe/Paris local time.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_stopA | Find Paris / Île-de-France stations and stops by name and return their IDs. |
| next_departuresA | Get the next real-time departures at a station, with minutes until departure. |
| plan_journeyA | Plan a public transport journey between two places in Île-de-France. |
| traffic_disruptionsA | Get current traffic disruptions, incidents and works on the Île-de-France network. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Each tool maps to a clearly distinct transit task: station lookup, real-time departures, journey planning, and disruption status. There is little risk of misselection, and descriptions reinforce the boundaries between tools.
Two tools follow a verb_noun pattern (search_stop, plan_journey), but next_departures is an adjective_noun phrase and traffic_disruptions is a noun_noun phrase. The names are readable and individually clear, but the set does not follow one predictable convention.
Four tools is well-scoped for a focused Île-de-France transit query server. Each tool serves a distinct core user need, and there are no redundant or filler tools.
The server covers the main transit workflows: finding stops, checking next departures, planning journeys, and viewing disruptions. Minor gaps remain, such as line-level details, fare information, or accessibility-specific queries, but agents can handle core tasks without dead ends.