RailCore Developers MCP server
tech.railcore/developersrailcore.techstreamable-httpv1.1.0Scanned
Indian Railways API docs and code samples, plus your RailCore usage, keys and live test requests.
8 tools: 1 do something that can't be undone, 1 change things and 6 only read.
- Reads private data · 3
- Reads text others write · 3
- Can send data out · 4
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here does something that can't be undone. Govern it.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the RailCore Developers MCP server can do
The RailCore Developers MCP server is published by railcore.tech, a domain the MCP Registry verified. It has 8 tools. It can do things that cannot be undone, such as sending, paying or publishing (try_endpoint) and create or change data (1 tool: explain_error), but cannot delete data. 6 tools only read.
3 tools read private data (search_docs, get_my_usage and list_my_keys); 3 tools bring in text other people can write (get_endpoint, get_code_sample and try_endpoint); 4 tools can send data out of your system (get_endpoint, get_code_sample, explain_error and 1 more). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 20, 2026, version 1.1.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
8 tools
Can't be undone 1Claude Code: ask
try_endpointSend 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.Reads text others writeCan send data outNo findings
Why it is in this group
- The description's first verb is "send": a word for sending, and what is sent cannot be taken back.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe description's first verb is "send": it sends or publishes something to other people.
- outboundThe input takes a URL (input.endpoint): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: false
- idempotentHint: false
- openWorldHint: true
- destructiveHint: false
Changes things 1Claude Code: ask
explain_errorWhat a RailCore API error means and how to fix it.Can send data out1 finding
Why it is in this group
- The name "explain_error" says "explain": a word for reading.
- The input takes a statement or command to run (input.code), which can change anything it can reach.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- outboundThe input takes a URL (input.endpoint): a request to a URL can carry data to whoever runs it.
Findings
- Warn
The server marks "explain_error" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "explain_error" says "explain": a word for reading.
Description, as the server wrote 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.
Annotations the server declares
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
- destructiveHint: false
Only reads 6Show 6 read-only tools
get_code_sampleWorking code for a RailCore API endpoint in curl, Node.js, Python, PHP, Go or Java.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "get_code_sample" says "get": a word for reading.
What it can reach
- untrusted-inputThe input takes a URL (input.endpoint), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.endpoint): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
- destructiveHint: false
get_endpointDetails 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, res…Reads text others writeCan send data outNo findings
Why it is in this group
- The name "get_endpoint" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "url": it reads web pages, which anyone can write.
- untrusted-inputThe input takes a URL (input.endpoint), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.endpoint): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
- destructiveHint: false
get_my_usageYour 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…Reads private dataNo findings
Why it is in this group
- The name "get_my_usage" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "doc": it reads documents.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
- destructiveHint: false
get_plansRailCore 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.No findings
Why it is in this group
- The name "get_plans" says "get": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
- destructiveHint: false
list_my_keysYour 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 u…Reads private dataNo findings
Why it is in this group
- The name "list_my_keys" says "list": a word for reading.
What it can reach
- private-dataThe description's first sentence says "secret": it reads secrets.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
- destructiveHint: false
search_docsSearch the RailCore Indian Railways API documentation: guides (authentication, request signing, rate limits, billing in requests), endpoint pages and error codes.Reads private dataNo findings
Why it is in this group
- The name "search_docs" says "search": a word for reading.
What it can reach
- private-dataThe name "search_docs" says "search" and "doc": it reads documents.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
- destructiveHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
36 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 3 untrusted-input tools breaks every one.
- Reads private data3
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write3
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out4
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__developers__get_code_sample",
"mcp__developers__get_endpoint",
"mcp__developers__try_endpoint"
]
}
}Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:20 UTC, unchanged since Nov 20, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 2
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://mcp.railcore.tech/.well-known/oauth-protected-resource/developers/mcp
- Authorization servers
- https://api.railcore.tech
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- yes
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 2 tools that change things (1 irreversible, 1 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://mcp.railcore.tech/developers/mcp: tools/list returned 8 tools to an anonymous client, including try_endpoint (irreversible), explain_error (write)
Findings
Matches of fixed checks, with the text they matched.
- Warnexplain_error
The server marks "explain_error" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "explain_error" says "explain": a word for reading.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools3 added.+3 addedView diff
- Added:get_my_usageOnly reads
- Added:list_my_keysOnly reads
- Added:try_endpointCan't be undone
Install
Pinned to version 1.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http developers https://mcp.railcore.tech/developers/mcpclaude mcp add --transport http developers https://mcp.railcore.tech/developers/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__developers__search_docs",
"mcp__developers__get_plans",
"mcp__developers__get_my_usage",
"mcp__developers__list_my_keys"
],
"ask": [
"mcp__developers__get_endpoint",
"mcp__developers__get_code_sample",
"mcp__developers__explain_error",
"mcp__developers__try_endpoint"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as developers. Review it before you use it.
Capability tags behind 7 rules
- mcp__developers__search_docs private-data
- mcp__developers__get_endpoint untrusted-input, outbound
- mcp__developers__get_code_sample untrusted-input, outbound
- mcp__developers__explain_error outbound
- mcp__developers__get_my_usage private-data
- mcp__developers__list_my_keys private-data
- mcp__developers__try_endpoint untrusted-input, outbound
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/tech.railcore/developers/verify?hash=18d982da17c1e47b7976a98c5fec1ae173680fe06df9c249c1fc1adadba18cd6" | jq -e '.changed == false'Pinned hash 18d982da17c1, from Nov 20, 2026, 12:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/tech.railcore/developers/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/tech.railcore/developers)Source: MCP Registry. Synced Nov 20, 2026, 12:18 UTC.
RailCore Developers MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the RailCore Developers MCP server safe?
- No scan can promise that. What its definitions show: 8 tools, 2 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the RailCore Developers MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the RailCore Developers MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: try_endpoint.
What tools does the RailCore Developers MCP server have?
- 8 tools: 1 irreversible, 1 write, 6 read. try_endpoint, explain_error, search_docs, get_endpoint, get_code_sample, get_plans, get_my_usage and list_my_keys.
Does the RailCore Developers MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the RailCore Developers MCP server send data to outside services?
- 4 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): get_endpoint, get_code_sample, explain_error and try_endpoint.
Has the RailCore Developers MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 20, 2026. Every change is on this page and in its Atom feed.