
Docs for the RailCore Indian Railways API: endpoints, signed code samples, error fixes and plans.
Maintained byrailcore.tech(verified)Also a maintainer?
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
What a RailCore API error means and how to fix it. Pass the error code (QUOTA_NOT_SUPPORTED), the HTTP status, or the whole error response. Never paste an API key or signing secret; any key-shaped text is removed before it is read.
The error code, such as QUOTA_NOT_SUPPORTED.
The HTTP status, such as 422.
The endpoint the request went to, if known.
The error response body. Remove any API key or secret first.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http developers https://mcp.railcore.tech/developers/mcp
Tool list last changed Nov 20, 2026.
What a RailCore API error means and how to fix it. Pass the error code (QUOTA_NOT_SUPPORTED), the HTTP status, or the whole error response. Never paste an API key or signing secret; any key-shaped text is removed before it is read.
| Argument | Type | Description |
|---|---|---|
| code | string | The error code, such as QUOTA_NOT_SUPPORTED. |
| status | integer | The HTTP status, such as 422. |
| endpoint | string | The endpoint the request went to, if known. |
| error_json | string | The error response body. Remove any API key or secret first. |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"code": {
"type": "string",
"maxLength": 80,
"description": "The error code, such as QUOTA_NOT_SUPPORTED."
},
"status": {
"type": "integer",
"maximum": 599,
"minimum": 100,
"description": "The HTTP status, such as 422."
},
"endpoint": {
"type": "string",
"maxLength": 300,
"description": "The endpoint the request went to, if known."
},
"error_json": {
"type": "string",
"maxLength": 20000,
"description": "The error response body. Remove any API key or secret first."
}
}
}Working code for a RailCore API endpoint in curl, Node.js, Python, PHP, Go or Java. Set signed to true for Growth, Scale and Enterprise keys, which must sign every request with HMAC-SHA256. Samples read the key from RAILCORE_KEY and the signing secret from RAILCORE_HMAC_SECRET, and work out their dates when they run.
| Argument | Type | Description |
|---|---|---|
| signed | boolean | true for Growth, Scale and Enterprise keys, which must sign every request. Default: true only for endpoints that signing plans alone can use. |
| endpoint* | string | An endpoint id, a method and path, or a URL. |
| language* | string | curl, node, python, php, go or java. |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"endpoint",
"language"
],
"properties": {
"signed": {
"type": "boolean",
"description": "true for Growth, Scale and Enterprise keys, which must sign every request. Default: true only for endpoints that signing plans alone can use."
},
"endpoint": {
"type": "string",
"maxLength": 300,
"minLength": 1,
"description": "An endpoint id, a method and path, or a URL."
},
"language": {
"enum": [
"curl",
"node",
"python",
"php",
"go",
"java"
],
"type": "string",
"description": "curl, node, python, php, go or java."
}
}
}Details of one RailCore API endpoint: method and URL, parameters, what it costs in requests, the key scope it needs, which plans can use it and whether requests must be signed, response fields and the errors it can answer. Accepts an endpoint id (seat-availability), a method and path (GET /trains/{train_number}/live) or a full URL.
| Argument | Type | Description |
|---|---|---|
| detail | string | summary (default) or full, which adds response fields and a response example. |
| endpoint* | string | An endpoint id (seat-availability), a method and path (GET /availability/seats) or a URL. |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"endpoint"
],
"properties": {
"detail": {
"enum": [
"summary",
"full"
],
"type": "string",
"description": "summary (default) or full, which adds response fields and a response example."
},
"endpoint": {
"type": "string",
"maxLength": 300,
"minLength": 1,
"description": "An endpoint id (seat-availability), a method and path (GET /availability/seats) or a URL."
}
}
}Your RailCore API plan and this month's usage: requests used and left, the per-minute and per-day limits, use per API key and in the docs playground, and when the allowance refills. Requires sign-in to your RailCore account.
No arguments.
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {}
}RailCore API plans: monthly price in INR, requests a month, per minute and per day, which plans must sign requests, IP allowlists, and which include charts and jobs. Pass a plan name to see one plan.
| Argument | Type | Description |
|---|---|---|
| plan | string | A plan name or id, such as Growth. Leave out to compare all plans. |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"plan": {
"type": "string",
"maxLength": 60,
"description": "A plan name or id, such as Growth. Leave out to compare all plans."
}
}
}Your active RailCore API keys: label, the first characters of the key, scopes, whether a signing secret is set, how many IP addresses are allowed, and when each was created, last used and expires. Never a full key or secret. Requires sign-in to your RailCore account.
No arguments.
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {}
}Search the RailCore Indian Railways API documentation: guides (authentication, request signing, rate limits, billing in requests), endpoint pages and error codes. Returns the best matching sections with links. Use it for any how-to question about the API.
| Argument | Type | Description |
|---|---|---|
| kind | string | Limit results to guides, endpoints or errors. Default: any. |
| limit | integer | How many results, 1 to 10. Default: 5. |
| query* | string | What to look for, in plain words or an error code. |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"query"
],
"properties": {
"kind": {
"enum": [
"any",
"guide",
"endpoint",
"error"
],
"type": "string",
"description": "Limit results to guides, endpoints or errors. Default: any."
},
"limit": {
"type": "integer",
"maximum": 10,
"minimum": 1,
"description": "How many results, 1 to 10. Default: 5."
},
"query": {
"type": "string",
"maxLength": 200,
"minLength": 1,
"description": "What to look for, in plain words or an error code."
}
}
}Send one real request to a RailCore API read endpoint with your account and return its answer: status, request ID, requests counted and left, and the response body. It counts against your plan like any API request, so ask the user first. max_requests caps what it may count (default 1); a request that would count more is refused before it is sent. At most 30 tries an hour. Requires sign-in to your RailCore account. The first try also asks permission to make test requests.
| Argument | Type | Description |
|---|---|---|
| body | string | The JSON body as text, for the two POST endpoints only (batch-seat-availability, compare-journeys), such as {"journeys": [{"from": "BSL", "to": "ADI", "date": "2026-12-01"}]}. |
| params | object | Path and query parameters by name, every value as a string, such as {"q": "pune", "limit": "5"} or {"train_number": "12951"}. Dates as YYYY-MM-DD. |
| endpoint* | string | A read endpoint: an id (search-stations), a method and path (GET /stations/search) or a URL. |
| max_requests | integer | The most requests this try may count, 1 to 25. Default 1. Raise it only after the user agrees to the cost. |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"endpoint"
],
"properties": {
"body": {
"type": "string",
"maxLength": 65536,
"description": "The JSON body as text, for the two POST endpoints only (batch-seat-availability, compare-journeys), such as {\"journeys\": [{\"from\": \"BSL\", \"to\": \"ADI\", \"date\": \"2026-12-01\"}]}."
},
"params": {
"type": "object",
"description": "Path and query parameters by name, every value as a string, such as {\"q\": \"pune\", \"limit\": \"5\"} or {\"train_number\": \"12951\"}. Dates as YYYY-MM-DD.",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "string"
}
},
"endpoint": {
"type": "string",
"maxLength": 300,
"minLength": 1,
"description": "A read endpoint: an id (search-stations), a method and path (GET /stations/search) or a URL."
},
"max_requests": {
"type": "integer",
"maximum": 25,
"minimum": 1,
"description": "The most requests this try may count, 1 to 25. Default 1. Raise it only after the user agrees to the cost."
}
}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 20, 2026.
What changed in this server's tools since we started watching, newest first. Each change is scanned again.
Send one real request to a RailCore API read endpoint with your account and return its answer: status, request ID, requests counted and left, and the response body. It counts against your plan like any API request, so ask the user first. max_requests caps what it may count (default 1); a request that would count more is refused before it is sent. At most 30 tries an hour. Requires sign-in to your RailCore account. The first try also asks permission to make test requests.
Your active RailCore API keys: label, the first characters of the key, scopes, whether a signing secret is set, how many IP addresses are allowed, and when each was created, last used and expires. Never a full key or secret. Requires sign-in to your RailCore account.
Your RailCore API plan and this month's usage: requests used and left, the per-minute and per-day limits, use per API key and in the docs playground, and when the allowance refills. Requires sign-in to your RailCore account.