Skip to content

Railflag MCP server

com.railflag/railflagrailflag.comstreamable-httpv0.1.0Scanned

Create, target and roll out feature flags. Production changes wait for a person to approve.

29 tools: 2 can delete or cancel things, 13 change things and 14 only read.

Tools: 2 delete, 0 irreversible, 13 write, 14 read.
  • Reads private data · 1
  • Reads text others write · 2
  • Can send data out · 0
  • 8 findings

Tools listed without sign-in. Remote posture

With Anlyon

2 tools here can delete or cancel things. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

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 Railflag MCP server can do

The Railflag MCP server is published by railflag.com, a domain the MCP Registry verified. It has 29 tools. It can delete or cancel things (2 tools: rollback_run and disconnect_source) and create or change data (13 tools: create_flag, toggle_flag, update_targeting, set_rollout and 9 more). 14 tools only read.

1 tool reads private data (get_code_guide); 2 tools bring in text other people can write (get_plan and compare_decisions).

The fixed checks matched 8 findings (base64-blob, credentials-mention and annotation-conflict). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 19, 2026, version 0.1.0.

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.

29 tools

Deletes or cancels 2Claude Code: deny
  • disconnect_sourceDeletes the stored credentials for a source connection.1 finding

    Why it is in this group

    • The description's first verb is "delete": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).

    Findings

    • Info

      The description mentions "credentials".

      Matched text

      description: "Deletes the stored credentials for a source connection."

      What this check looks for
    Description, as the server wrote it
    Deletes the stored credentials for a source connection.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • openWorldHint: false
  • rollback_runUndoes one apply run: restores previous targeting and archives flags it created.No findings

    Why it is in this group

    • The name "rollback_run" says "run": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Undoes one apply run: restores previous targeting and archives flags it created.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • openWorldHint: false
Changes things 13Claude Code: ask
  • apply_planWrites the plan into one Railflag environment.No findings

    Why it is in this group

    • The name "apply_plan" says "apply": a word for a change.
    Description, as the server wrote it
    Writes the plan into one Railflag environment. Running it again changes nothing. Environments that need approval return an approvalUrl for a person. Never writes to the source vendor.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • openWorldHint: false
    • idempotentHint: true
  • connect_monitoringStarts connecting Prometheus/Grafana, Datadog, Sentry, New Relic or a Slack channel for alerts.1 finding

    Why it is in this group

    • The description's first verb is "start": a word for a change.

    Findings

    • Info

      The description mentions "credentials".

      Matched text

      description: "...nk: give it to the user, who enters the credentials there. Never ask the user for credentia..."

      What this check looks for
    Description, as the server wrote it
    Starts connecting Prometheus/Grafana, Datadog, Sentry, New Relic or a Slack channel for alerts. Returns a one-time link: give it to the user, who enters the credentials there. Never ask the user for credentials in chat. Admins only.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • openWorldHint: false
  • connect_sourceStarts a read-only connection to the user's account at another flag vendor (see list_sources).1 finding

    Why it is in this group

    • The description's first verb is "start": a word for a change.

    Findings

    • Info

      The description mentions "credentials".

      Matched text

      description: "...ns a link the user opens to enter their credentials there. Never ask the user to paste cred..."

      What this check looks for
    Description, as the server wrote it
    Starts a read-only connection to the user's account at another flag vendor (see list_sources). Returns a link the user opens to enter their credentials there. Never ask the user to paste credentials into the chat. After they finish, call get_connection.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • openWorldHint: false
  • create_flagCreates a flag, off in every environment.No findings

    Why it is in this group

    • The name "create_flag" says "create": a word for a change.
    Description, as the server wrote it
    Creates a flag, off in every environment. Boolean flags have variations [false, true].

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • openWorldHint: false
  • monitoring_coverageThe project's monitoring coverage: live Production flags nobody watches (ranked by risk), kill switches never tested, flags no SDK evaluates, and services missing error or latency …No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    The project's monitoring coverage: live Production flags nobody watches (ranked by risk), kill switches never tested, flags no SDK evaluates, and services missing error or latency metrics. Business plan.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • plan_migrationBuilds a dry-run plan from the latest scan.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Builds a dry-run plan from the latest scan. envMap maps source environment ids (from get_connection or the scan) to Railflag environment keys, e.g. {"production": "staging"} to try production data in staging first. Nothing is written.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • openWorldHint: false
    • idempotentHint: true
  • scan_sourceReads all flags and their targeting from the connected vendor (read only).1 finding

    Why it is in this group

    • The description's first verb is "read": a word for reading.
    • The server marks it as not read-only (readOnlyHint: false).

    Findings

    • Warn

      The server marks "scan_source" as not read-only (readOnlyHint: false), and its words say it reads.

      Matched text

      annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "read": a word for reading.

      What this check looks for
    Description, as the server wrote it
    Reads all flags and their targeting from the connected vendor (read only). Runs in the background: poll get_run with the returned runId.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • openWorldHint: false
    • idempotentHint: true
  • set_rolloutSets the percentage split for the default rule, or for one rule by id.No findings

    Why it is in this group

    • The name "set_rollout" says "set": a word for a change.
    Description, as the server wrote it
    Sets the percentage split for the default rule, or for one rule by id. percentages has one number per variation and must add up to 100 (e.g. [80, 20] gives 20% true for a boolean flag). Raising a percentage only adds users.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • openWorldHint: false
  • stop_watchStops watching.No findings

    Why it is in this group

    • The name "stop_watch" says "stop": a word for a change.
    Description, as the server wrote it
    Stops watching. Doesn't change the flag.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • openWorldHint: false
  • suggest_watch_planDrafts a Release Watch plan for a flag change: which signals to monitor (error rate, latency, conversions, new Sentry issues, the rollout split), the limits, and for how long.2 findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.

    Findings

    • Warn

      The input schema at properties.targeting.properties.rules.items.properties.serve.anyOf[0].$ref contains a 52-character base64 string.

      Matched text

      inputSchema.properties.targeting.properties.rules.items.properties.serve.anyOf[0].$ref: "#/properties/targeting/properties/fallthrough/anyOf/0"

      What this check looks for
    • Warn

      The input schema at properties.targeting.properties.rules.items.properties.serve.anyOf[1].$ref contains a 52-character base64 string.

      Matched text

      inputSchema.properties.targeting.properties.rules.items.properties.serve.anyOf[1].$ref: "#/properties/targeting/properties/fallthrough/anyOf/1"

      What this check looks for
    Description, as the server wrote it
    Drafts a Release Watch plan for a flag change: which signals to monitor (error rate, latency, conversions, new Sentry issues, the rollout split), the limits, and for how long. Describe the change with percentages (default rule split, like set_rollout), enabled (on/off) or a full targeting. Returns a watchPlanId to pass to the change tool. On plans without Release Watch it says what it would monitor instead.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • openWorldHint: false
  • toggle_flagTurns a flag on or off in one environment.No findings

    Why it is in this group

    • The name "toggle_flag" says "toggle": a word for a change.
    Description, as the server wrote it
    Turns a flag on or off in one environment. In environments that need approval this returns an approvalUrl for a person.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • openWorldHint: false
  • update_planRecords decisions on issues.No findings

    Why it is in this group

    • The name "update_plan" says "update": a word for a change.
    Description, as the server wrote it
    Records decisions on issues. Each issue lists its allowed actions: skip_flag, drop_rule, keep, rename (value = new key), overwrite. Info issues need no decision. Ask the user when the choice is not obviously safe.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • openWorldHint: false
  • update_targetingReplaces a flag's targeting in one environment.2 findings

    Why it is in this group

    • The name "update_targeting" says "update": a word for a change.

    Findings

    • Warn

      The input schema at properties.targeting.properties.rules.items.properties.serve.anyOf[0].$ref contains a 52-character base64 string.

      Matched text

      inputSchema.properties.targeting.properties.rules.items.properties.serve.anyOf[0].$ref: "#/properties/targeting/properties/fallthrough/anyOf/0"

      What this check looks for
    • Warn

      The input schema at properties.targeting.properties.rules.items.properties.serve.anyOf[1].$ref contains a 52-character base64 string.

      Matched text

      inputSchema.properties.targeting.properties.rules.items.properties.serve.anyOf[1].$ref: "#/properties/targeting/properties/fallthrough/anyOf/1"

      What this check looks for
    Description, as the server wrote it
    Replaces a flag's targeting in one environment. Read it with get_flag first and pass its version as baseVersion so you never overwrite someone else's change. Rules are checked top to bottom; the first match wins.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • openWorldHint: false
Only reads 14Show 14 read-only tools
  • compare_decisionsAsks the source vendor what sample users get (AB Tasty: Decision API, needs a Decision API key on the connection; Unleash: its server-side playground) without recording anything, a…Reads text others writeNo findings

    Why it is in this group

    • The name "compare_decisions" says "compare": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Asks the source vendor what sample users get (AB Tasty: Decision API, needs a Decision API key on the connection; Unleash: its server-side playground) without recording anything, and compares with the plan. Runs in the background: poll get_run.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • explain_itemThe source vendor's definition of one flag next to what it becomes in Railflag, and its issues.No findings

    Why it is in this group

    • The name "explain_item" says "explain": a word for reading.
    Description, as the server wrote it
    The source vendor's definition of one flag next to what it becomes in Railflag, and its issues.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • get_change_requestStatus of a change waiting for approval: pending, applied, rejected or failed.No findings

    Why it is in this group

    • The name "get_change_request" says "get": a word for reading.
    Description, as the server wrote it
    Status of a change waiting for approval: pending, applied, rejected or failed.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • get_code_guideHow to rewrite the source vendor's SDK calls to OpenFeature with Railflag: setup, regex patterns, before/after examples, notes.Reads private dataNo findings

    Why it is in this group

    • The name "get_code_guide" says "get": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "note": it reads notes.
    Description, as the server wrote it
    How to rewrite the source vendor's SDK calls to OpenFeature with Railflag: setup, regex patterns, before/after examples, notes. Apply it in the user's repo yourself and show them the diff.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • get_connectionWhether the user finished connecting, which source environments are visible, and whether decisions can be compared.No findings

    Why it is in this group

    • The name "get_connection" says "get": a word for reading.
    Description, as the server wrote it
    Whether the user finished connecting, which source environments are visible, and whether decisions can be compared.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • get_flagOne flag: variations and full targeting in every environment, with versions for safe updates.No findings

    Why it is in this group

    • The name "get_flag" says "get": a word for reading.
    Description, as the server wrote it
    One flag: variations and full targeting in every environment, with versions for safe updates.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • get_historyAudit log for the project or one flag: who changed what, when and why.No findings

    Why it is in this group

    • The name "get_history" says "get": a word for reading.
    Description, as the server wrote it
    Audit log for the project or one flag: who changed what, when and why.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • get_planA plan's summary, issues and items.Reads text others writeNo findings

    Why it is in this group

    • The name "get_plan" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "issue": it reads issues, which other people can write.
    Description, as the server wrote it
    A plan's summary, issues and items. full=true includes each item's targeting.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • get_runStatus and result of a scan, compare or apply run.No findings

    Why it is in this group

    • The name "get_run" says "get": a word for reading.
    Description, as the server wrote it
    Status and result of a scan, compare or apply run.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • get_watchA watch: its status (draft, active, passed, paused, stopped), each signal's state, the timeline and the verdict.No findings

    Why it is in this group

    • The name "get_watch" says "get": a word for reading.
    Description, as the server wrote it
    A watch: its status (draft, active, passed, paused, stopped), each signal's state, the timeline and the verdict.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • list_environmentsEnvironments, whether they require approval, and their published config versions.No findings

    Why it is in this group

    • The name "list_environments" says "list": a word for reading.
    Description, as the server wrote it
    Environments, whether they require approval, and their published config versions. Keys are not returned.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • list_flagsAll flags with their state in each environment.No findings

    Why it is in this group

    • The name "list_flags" says "list": a word for reading.
    Description, as the server wrote it
    All flags with their state in each environment.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • list_sourcesVendors Railflag can import flags from, what it reads from each, and which are coming later.No findings

    Why it is in this group

    • The name "list_sources" says "list": a word for reading.
    Description, as the server wrote it
    Vendors Railflag can import flags from, what it reads from each, and which are coming later.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • list_watchesWatches in the project, newest first, optionally for one flag and by status (comma separated: draft, active, passed, paused, stopped, expired).No findings

    Why it is in this group

    • The name "list_watches" says "list": a word for reading.
    Description, as the server wrote it
    Watches in the project, newest first, optionally for one flag and by status (comma separated: draft, active, passed, paused, stopped, expired).

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: 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.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged outbound.

Reads private data1
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write2
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

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.

Tools listed without sign-in

Looked at Nov 19, 2026, 17:19 UTC, unchanged since Nov 19, 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
15
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 15 tools that change things (2 destructive, 13 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://mcp.railflag.com/mcp: tools/list returned 29 tools to an anonymous client, including rollback_run (destructive), disconnect_source (destructive), create_flag (write), toggle_flag (write), update_targeting (write) and 10 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

5 warn3 info
  • The input schema at properties.targeting.properties.rules.items.properties.serve.anyOf[0].$ref contains a 52-character base64 string.

    Matched text

    inputSchema.properties.targeting.properties.rules.items.properties.serve.anyOf[0].$ref: "#/properties/targeting/properties/fallthrough/anyOf/0"

    What this check looks for
  • The input schema at properties.targeting.properties.rules.items.properties.serve.anyOf[1].$ref contains a 52-character base64 string.

    Matched text

    inputSchema.properties.targeting.properties.rules.items.properties.serve.anyOf[1].$ref: "#/properties/targeting/properties/fallthrough/anyOf/1"

    What this check looks for
  • The input schema at properties.targeting.properties.rules.items.properties.serve.anyOf[0].$ref contains a 52-character base64 string.

    Matched text

    inputSchema.properties.targeting.properties.rules.items.properties.serve.anyOf[0].$ref: "#/properties/targeting/properties/fallthrough/anyOf/0"

    What this check looks for
  • The input schema at properties.targeting.properties.rules.items.properties.serve.anyOf[1].$ref contains a 52-character base64 string.

    Matched text

    inputSchema.properties.targeting.properties.rules.items.properties.serve.anyOf[1].$ref: "#/properties/targeting/properties/fallthrough/anyOf/1"

    What this check looks for
  • The server marks "scan_source" as not read-only (readOnlyHint: false), and its words say it reads.

    Matched text

    annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "read": a word for reading.

    What this check looks for
  • The description mentions "credentials".

    Matched text

    description: "...nk: give it to the user, who enters the credentials there. Never ask the user for credentia..."

    What this check looks for
Show 2 more findings

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 0.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http railflag https://mcp.railflag.com/mcp --header 'Authorization: <your-authorization>'
claude mcp add --transport http railflag https://mcp.railflag.com/mcp --header 'Authorization: <your-authorization>'

Run 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.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__railflag__list_flags",
      "mcp__railflag__get_flag",
      "mcp__railflag__list_environments",
      "mcp__railflag__get_history",
      "mcp__railflag__get_change_request",
      "mcp__railflag__get_watch",
      "mcp__railflag__list_watches",
      "mcp__railflag__list_sources",
      "mcp__railflag__get_connection",
      "mcp__railflag__get_run",
      "mcp__railflag__get_plan",
      "mcp__railflag__explain_item",
      "mcp__railflag__compare_decisions",
      "mcp__railflag__get_code_guide"
    ],
    "ask": [
      "mcp__railflag__create_flag",
      "mcp__railflag__toggle_flag",
      "mcp__railflag__update_targeting",
      "mcp__railflag__set_rollout",
      "mcp__railflag__suggest_watch_plan",
      "mcp__railflag__stop_watch",
      "mcp__railflag__monitoring_coverage",
      "mcp__railflag__connect_monitoring",
      "mcp__railflag__connect_source",
      "mcp__railflag__scan_source",
      "mcp__railflag__plan_migration",
      "mcp__railflag__update_plan",
      "mcp__railflag__apply_plan"
    ],
    "deny": [
      "mcp__railflag__rollback_run",
      "mcp__railflag__disconnect_source"
    ]
  }
}

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 railflag. Review it before you use it.

Capability tags behind 3 rules
  • mcp__railflag__get_plan untrusted-input
  • mcp__railflag__compare_decisions untrusted-input
  • mcp__railflag__get_code_guide private-data

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/com.railflag/railflag/verify?hash=9cc87c22c106918a7cfd1d72615ee6880ce0de337e0dc062874654d478d83c6a" | jq -e '.changed == false'

Pinned hash 9cc87c22c106, from Nov 19, 2026, 07:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/com.railflag/railflag/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for com.railflag/railflag
[![Anlyon Radar](https://radar.anlyon.com/badge/com.railflag/railflag.svg)](https://radar.anlyon.com/servers/com.railflag/railflag)

Source: MCP Registry. Synced Nov 19, 2026, 07:17 UTC.

Railflag MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Railflag MCP server safe?

No scan can promise that. What its definitions show: 29 tools, 15 of which can change, send or delete something, and 8 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the Railflag MCP server delete data?

Yes. 2 tools can delete, cancel or revoke something: rollback_run and disconnect_source.

Can the Railflag MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the Railflag MCP server have?

29 tools: 2 destructive, 13 write, 14 read. rollback_run, disconnect_source, create_flag, toggle_flag, update_targeting, set_rollout, suggest_watch_plan, stop_watch and 21 more.

Does the Railflag MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Railflag MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the Railflag MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 19, 2026.