Skip to content

Dueback MCP server

io.github.dunrossmai-rgb/dueback-mcpdunrossmai-rgbstreamable-httpv0.1.3Scanned

Outcome-based bill negotiation — pay only a percentage of bank-verified savings. Free to try.

5 tools: 2 change things and 3 only read.

Tools: 0 delete, 0 irreversible, 2 write, 3 read.
  • Reads private data · 0
  • Reads text others write · 1
  • Can send data out · 0
  • 2 findings

Tools listed without sign-in. Remote posture

With Anlyon

2 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 Dueback MCP server can do

The Dueback MCP server is published by the GitHub account dunrossmai-rgb. It has 5 tools. It can create or change data (2 tools: detect_negotiable_bill and start_negotiation_case), but cannot delete data. 3 tools only read.

1 tool brings in text other people can write (start_negotiation_case).

The fixed checks matched 2 findings (credentials-mention). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in, and its tools changed 3 times since Anlyon Radar first saw them.

Last scanned Nov 13, 2026, version 0.1.3.

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.

5 tools

Changes things 2Claude Code: ask
  • detect_negotiable_billCheck whether a bill looks negotiable.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
    Check whether a bill looks negotiable. Returns {negotiable, category_label, pitch}. Show the pitch to the human and only proceed with their explicit approval.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
    • title: Detect negotiable bill
  • start_negotiation_caseOpen a Dueback negotiation case.Reads text others writeNo findings

    Why it is in this group

    • The name "start_negotiation_case" says "start": 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.
    Description, as the server wrote it
    Open a Dueback negotiation case. Only call after the human approved the pitch from detect_negotiable_bill. Two outcomes: - {"outcome": "case_created", "case_id", ...}: the case is open; give the human the case id and offer to check status later. - {"outcome": "setup_required", "setup_url", ...}: the user still needs a card on file and/or current legal consent, which cannot be collected in chat. Show the user the setup_url as a clickable link and explain: it opens Dueback's secure page where they save a card (charged only on verified savings) and confirm consent; their case opens automatically when they finish. Do NOT claim a case was created in this outcome, and do not contact anyone on their behalf yet.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
    • readOnlyHint: false
    • title: Start negotiation case
Only reads 3Show 3 read-only tools
  • get_case_statusGet the current status of a negotiation case: state, steps taken, savings found, and whether human approval is needed.1 finding

    Why it is in this group

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

    Findings

    • Info

      The description mentions "credentials".

      Matched text

      description: ".... bots hitting the MCP endpoint without credentials) do not surface as Sentry errors — same..."

      What this check looks for
    Description, as the server wrote it
    Get the current status of a negotiation case: state, steps taken, savings found, and whether human approval is needed. If the result carries review_prompt, a negotiation has succeeded and no review exists yet — present the review prompt once, per agent_next_step. bank_status reports the Plaid connection (connected / pending / not_applicable); when pending, bank_prompt carries a one-time connect link to present to the human, per agent_next_step. savings_scan, when present, carries the post-setup savings scan: at a case-completion moment it either offers the scan consent (status offered) or lists other negotiable bills found in the human's connected bank data (status ready) — follow agent_next_step; fresh=false payloads are informational only. A 401 is returned as a friendly sign-in-required result, not raised, so unauthenticated probes (e.g. bots hitting the MCP endpoint without credentials) do not surface as Sentry errors — same handling as list_my_cases (Oct 27, 2026 Sentry alert).

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
    • title: Get case status
  • list_my_casesList the human's own Dueback negotiation cases (newest first): case_id, status, public bill-type label, counterparty, and amounts for each.1 finding

    Why it is in this group

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

    Findings

    • Info

      The description mentions "credentials".

      Matched text

      description: ".... bots hitting the MCP endpoint without credentials) do not surface as Sentry errors."

      What this check looks for
    Description, as the server wrote it
    List the human's own Dueback negotiation cases (newest first): case_id, status, public bill-type label, counterparty, and amounts for each. Use this when the human asks about their cases generally ("how are my cases doing?") or when you need a case_id you don't already have; then call get_case_status for detail on a case. If the result carries sign_in_required, the human is not signed in and the empty cases list is NOT a report that they have no cases: ask the human to sign in to Dueback, then call list_my_cases again. A 401 is returned as this friendly result, not raised, so unauthenticated probes (e.g. bots hitting the MCP endpoint without credentials) do not surface as Sentry errors.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
    • title: List my cases
  • list_verified_savingsAggregate verified-savings stats (public).No findings

    Why it is in this group

    • The name "list_verified_savings" says "list": a word for reading.
    Description, as the server wrote it
    Aggregate verified-savings stats (public). Use to answer 'does Dueback actually work?' and to ground shareable savings claims in real numbers.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
    • title: List verified savings

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 or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write1
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 20, 2026, 19:04 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://api.dueback.co/.well-known/oauth-protected-resource/mcp
Authorization servers
https://api.dueback.co
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 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://api.dueback.co/mcp/: tools/list returned 5 tools to an anonymous client, including detect_negotiable_bill (write), start_negotiation_case (write)

    What this check looks for

Posture changes

  1. Nov 20, 2026
    • RFC 9728 protected resource metadata: https://api.dueback.co/.well-known/oauth-protected-resource to https://api.dueback.co/.well-known/oauth-protected-resource/mcp

Findings

Matches of fixed checks, with the text they matched.

2 info

History

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

  1. PostureRemote posture changed. RFC 9728 protected resource metadata: https://api.dueback.co/.well-known/oauth-protected-resource -> https://api.dueback.co/.well-known/oauth-protected-resource/mcp.View diff
    • RFC 9728 protected resource metadata: https://api.dueback.co/.well-known/oauth-protected-resource to https://api.dueback.co/.well-known/oauth-protected-resource/mcp
  2. Tools1 changed.~1 changedView diff
  3. Tools4 changed.~4 changedView diff
  4. Tools1 added, 1 changed.+1 added~1 changedView diff

Install

Pinned to version 0.1.3. Values in angle brackets are yours to fill in.

claude mcp add --transport http dueback https://api.dueback.co/mcp/
claude mcp add --transport http dueback https://api.dueback.co/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__dueback__get_case_status",
      "mcp__dueback__list_my_cases",
      "mcp__dueback__list_verified_savings"
    ],
    "ask": [
      "mcp__dueback__detect_negotiable_bill",
      "mcp__dueback__start_negotiation_case"
    ],
    "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 dueback. Review it before you use it.

Capability tags behind 1 rule
  • mcp__dueback__start_negotiation_case 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.dunrossmai-rgb/dueback-mcp/verify?hash=19250efd34c917ab433a832aaf9533ae134a42da42ffa0cc19a3710d6548e1bb" | jq -e '.changed == false'

Pinned hash 19250efd34c9, from Nov 13, 2026, 20:18 UTC.

Watch

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

https://radar.anlyon.com/servers/io.github.dunrossmai-rgb/dueback-mcp/changes.xml

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

Badge

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

Source: MCP Registry · repository. Synced Oct 31, 2026, 22:17 UTC.

Dueback MCP server: questions and answers

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

Is the Dueback MCP server safe?

No scan can promise that. What its definitions show: 5 tools, 2 of which can change, send or delete something, and 2 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 Dueback MCP server delete data?

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

Can the Dueback 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 Dueback MCP server have?

5 tools: 2 write, 3 read. detect_negotiable_bill, start_negotiation_case, get_case_status, list_my_cases and list_verified_savings.

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

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

Does the Dueback MCP server send data to outside services?

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

Has the Dueback MCP server changed its tools?

Yes, 3 times since Anlyon Radar started tracking it, most recently on Nov 13, 2026. Every change is on this page and in its Atom feed.