Skip to content

FluxProof MCP server

io.github.equinoxaifinance-rgb/fluxproofequinoxaifinance-rgbstreamable-httpv0.3.0Scanned

Evidence-bearing public webpage monitoring with hashes, diffs, signed webhooks, REST, and MCP.

6 tools: 3 change things and 3 only read.

Tools: 0 delete, 0 irreversible, 3 write, 3 read.
  • Reads private data · 0
  • Reads text others write · 3
  • Can send data out · 2
  • 4 findings

Tools listed without sign-in. Remote posture

With Anlyon

3 tools here change 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 FluxProof MCP server can do

The FluxProof MCP server is published by the GitHub account equinoxaifinance-rgb. It has 6 tools. It can create or change data (3 tools: fluxproof_get_free_key, fluxproof_create_monitor and fluxproof_check_now), but cannot delete data. 3 tools only read.

3 tools bring in text other people can write (fluxproof_preflight, fluxproof_create_monitor and fluxproof_check_now); 2 tools can send data out of your system (fluxproof_preflight and fluxproof_create_monitor).

The fixed checks matched 4 findings (credentials-mention). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in, and its tools changed 2 times since Anlyon Radar first saw them.

Last scanned Nov 9, 2026, version 0.3.0.

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.

6 tools

Changes things 3Claude Code: ask
  • fluxproof_check_nowRun a monitor now and return a source- and hash-bound change receipt.Reads text others write1 finding

    Why it is in this group

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

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

      The input schema at properties.api_key.description mentions "credential".

      Matched text

      inputSchema.properties.api_key.description: "Buyer-owned FluxProof API key; a secret credential."

      What this check looks for
    Description, as the server wrote it
    Run a monitor now and return a source- and hash-bound change receipt. Consumes check quota, stores a receipt and may deliver a configured webhook. Not an idempotent read.

    Annotations the server declares

    • title: Check a watched page now
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • fluxproof_create_monitorCreate a monitor using a buyer-owned FluxProof API key.Reads text others writeCan send data out1 finding

    Why it is in this group

    • The name "fluxproof_create_monitor" says "create": a word for a change.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.

    Findings

    • Info

      The input schema at properties.api_key.description mentions "credential".

      Matched text

      inputSchema.properties.api_key.description: "Buyer-owned FluxProof API key; a secret credential."

      What this check looks for
    Description, as the server wrote it
    Create a monitor using a buyer-owned FluxProof API key. Creates persistent state and performs a baseline check, consuming quota. Not idempotent: each call creates a new monitor.

    Annotations the server declares

    • title: Start watching a page
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • fluxproof_get_free_keyCreate a free FluxProof API key: one page, checked daily, for 30 days, no card.1 finding

    Why it is in this group

    • The name "fluxproof_get_free_key" says "get": a word for reading.
    • The description's first verb is "create": a word for a change.

    Findings

    • Info

      The description mentions "credential".

      Matched text

      description: "...he key is returned once and is a secret credential."

      What this check looks for
    Description, as the server wrote it
    Create a free FluxProof API key: one page, checked daily, for 30 days, no card. One per internet connection (IP address) per month. The key is returned once and is a secret credential.

    Annotations the server declares

    • title: Get a free API key
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
Only reads 3Show 3 read-only tools
  • fluxproof_list_changesList recent evidence receipts for a monitor.1 finding

    Why it is in this group

    • The name "fluxproof_list_changes" says "list": a word for reading.

    Findings

    • Info

      The input schema at properties.api_key.description mentions "credential".

      Matched text

      inputSchema.properties.api_key.description: "Buyer-owned FluxProof API key; a secret credential."

      What this check looks for
    Description, as the server wrote it
    List recent evidence receipts for a monitor.

    Annotations the server declares

    • title: List recorded changes
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • fluxproof_offerReturn free and paid boundaries and purchase routes without charging.No findings

    Why it is in this group

    • The description's first verb is "return": a word for reading.
    Description, as the server wrote it
    Return free and paid boundaries and purchase routes without charging. Returns the free daily plan, the $9 paid pass (30 days paid once; when offered, also $9 a month through the human checkout, cancel any time), the human checkout link and the agent payment route. Example: {}. Reading the offer charges nothing.

    Annotations the server declares

    • title: Show plans and prices
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • fluxproof_preflightFetch a public URL and return fetchability, size, final URL, title, and content hash without page content or payment.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The description's first verb is "fetch": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe description's first sentence says "fetch" and "url": it reads web pages, which anyone can write.
    • untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
    • outboundThe input takes a URL (input.url): 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
    Fetch a public URL and return fetchability, size, final URL, title, and content hash without page content or payment. How it works: given one public page address, FluxProof fetches it once and says whether it can watch it; nothing is created or charged. Example: {"url":"https://example.com/"}.

    Annotations the server declares

    • title: Check a public page (free)
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true

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 private-data.

Reads private data0
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 out2
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 20, 2026, 19:04 UTC, unchanged since Oct 29, 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
3
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
https://fluxproof.steellantern.com/.well-known/oauth-protected-resource
Authorization servers
https://fluxproof.steellantern.com
Legacy HTTP+SSE transport
no
Dynamic client registration
yes
Client ID metadata documents
no
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 3 tools that change things (3 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://fluxproof.steellantern.com/mcp: tools/list returned 6 tools to an anonymous client, including fluxproof_get_free_key (write), fluxproof_create_monitor (write), fluxproof_check_now (write)

    What this check looks for

Posture changes

  1. Oct 29, 2026
    • RFC 9728 protected resource metadata: https://fluxproof.tryneverclosed.com/.well-known/oauth-protected-resource to https://fluxproof.steellantern.com/.well-known/oauth-protected-resource
    • Authorization servers: https://fluxproof.tryneverclosed.com to https://fluxproof.steellantern.com

Findings

Matches of fixed checks, with the text they matched.

4 info

History

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

  1. Tools3 changed.~3 changedView diff
  2. PostureRemote posture changed. RFC 9728 protected resource metadata: https://fluxproof.tryneverclosed.com/.well-known/oauth-protected-resource -> https://fluxproof.steellantern.com/.well-known/oauth-protected-resource; Authorization servers: https…View diff
    • RFC 9728 protected resource metadata: https://fluxproof.tryneverclosed.com/.well-known/oauth-protected-resource to https://fluxproof.steellantern.com/.well-known/oauth-protected-resource
    • Authorization servers: https://fluxproof.tryneverclosed.com to https://fluxproof.steellantern.com
  3. Tools1 changed.~1 changedView diff

Install

Pinned to version 0.3.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http fluxproof https://fluxproof.steellantern.com/mcp
claude mcp add --transport http fluxproof https://fluxproof.steellantern.com/mcp

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__fluxproof__fluxproof_offer",
      "mcp__fluxproof__fluxproof_list_changes"
    ],
    "ask": [
      "mcp__fluxproof__fluxproof_preflight",
      "mcp__fluxproof__fluxproof_get_free_key",
      "mcp__fluxproof__fluxproof_create_monitor",
      "mcp__fluxproof__fluxproof_check_now"
    ],
    "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 fluxproof. Review it before you use it.

Capability tags behind 3 rules
  • mcp__fluxproof__fluxproof_preflight untrusted-input, outbound
  • mcp__fluxproof__fluxproof_create_monitor untrusted-input, outbound
  • mcp__fluxproof__fluxproof_check_now untrusted-input

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/io.github.equinoxaifinance-rgb/fluxproof/verify?hash=87e9526d032fc0e749e7329ddb9a88d03103605014be9dda24ff4fa4d94af4e6" | jq -e '.changed == false'

Pinned hash 87e9526d032f, from Nov 9, 2026, 16:17 UTC.

Watch

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

https://radar.anlyon.com/servers/io.github.equinoxaifinance-rgb/fluxproof/changes.xml

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

Badge

Anlyon Radar badge for io.github.equinoxaifinance-rgb/fluxproof
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.equinoxaifinance-rgb/fluxproof.svg)](https://radar.anlyon.com/servers/io.github.equinoxaifinance-rgb/fluxproof)

Source: MCP Registry · repository. Synced Oct 27, 2026, 14:17 UTC.

FluxProof MCP server: questions and answers

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

Is the FluxProof MCP server safe?

No scan can promise that. What its definitions show: 6 tools, 3 of which can change, send or delete something, and 4 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 FluxProof MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the FluxProof 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 FluxProof MCP server have?

6 tools: 3 write, 3 read. fluxproof_get_free_key, fluxproof_create_monitor, fluxproof_check_now, fluxproof_preflight, fluxproof_offer and fluxproof_list_changes.

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

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

Does the FluxProof MCP server send data to outside services?

2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): fluxproof_preflight and fluxproof_create_monitor.

Has the FluxProof MCP server changed its tools?

Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 9, 2026. Every change is on this page and in its Atom feed.