Skip to content

Boundra — Payment Approval Gateway for AI Agents MCP server

io.boundra/boundraboundra.iostreamable-httpv0.2.0Scanned

Allow, ask, or veto — a policy decision point your agent consults before signing any payment

14 tools: 1 can delete or cancel things, 1 do something that can't be undone, 5 change things and 7 only read.

Tools: 1 delete, 1 irreversible, 5 write, 7 read.
  • Reads private data · 0
  • Reads text others write · 0
  • Can send data out · 1
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here can delete or cancel things and 1 does something that can't be undone. 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 Boundra — Payment Approval Gateway for AI Agents MCP server can do

The Boundra — Payment Approval Gateway for AI Agents MCP server is published by boundra.io, a domain the MCP Registry verified. It has 14 tools. It can delete or cancel things (1 tool: revoke_policy), do things that cannot be undone, such as sending, paying or publishing (evaluate_payment) and create or change data (5 tools: settle_evaluation, release_evaluation, request_policy_change, set_policy and 1 more). 7 tools only read.

1 tool can send data out of your system (evaluate_payment).

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

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

Last scanned Nov 10, 2026, version 0.2.0.

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.

14 tools

Deletes or cancels 1Claude Code: deny
  • revoke_policy[USER ONLY] Revoke a policy chain (takes effect immediately; subsequent payments default to DENY).No findings

    Why it is in this group

    • The name "revoke_policy" says "revoke": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    [USER ONLY] Revoke a policy chain (takes effect immediately; subsequent payments default to DENY). Must carry the user's wallet signature over the revocation statement.

    Annotations the server declares

    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: false
Can't be undone 1Claude Code: ask
  • evaluate_paymentEvaluate a payment intent.Can send data outNo findings

    Why it is in this group

    • The name "evaluate_payment" says "evaluate": a word for a change.
    • The name "evaluate_payment" also says "payment": a word that usually means money moves, which cannot be taken back.
    • The input addresses people (input.recipient): what it sends cannot be taken back.

    What it can reach

    • outboundThe input takes a destination (input.recipient): what the tool writes goes there.
    Description, as the server wrote it
    Evaluate a payment intent. MUST be called before executing any payment. ALLOW = you may pay; DENY = you must abandon; ASK = a challenge is returned — relay the reason to the user, then retry with approval_token once the user signs. An optional mandate parameter carries a user-issued single-task authorization.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
    • readOnlyHint: false
Changes things 5Claude Code: ask
  • release_evaluationRelease a reserved ALLOW budget when the payment failed or was abandoned.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
    Release a reserved ALLOW budget when the payment failed or was abandoned. Requires the evaluation_id and reservation_token returned by evaluate_payment.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: false
  • render_templateRender a natural-language rule from a template + parameters (then compile, sign & publish)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
    Render a natural-language rule from a template + parameters (then compile, sign & publish)

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
  • request_policy_change[For agents] Ask the user for a policy/budget change (e.g.No findings

    Why it is in this group

    • The name "request_policy_change" says "request": a word for a change.
    Description, as the server wrote it
    [For agents] Ask the user for a policy/budget change (e.g. 'raise daily budget from 50 to 80'). The request is queued for user approval; the user signs and publishes a new policy version. Agents can NEVER change policy directly.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
    • readOnlyHint: false
  • set_policy[USER ONLY] Submit a new policy version.No findings

    Why it is in this group

    • The name "set_policy" says "set": a word for a change.
    Description, as the server wrote it
    [USER ONLY] Submit a new policy version. Must carry the user's wallet EIP-191 signature over the policy document; accepted only after signature + version-chain checks pass. Agents MUST NOT call this tool.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
    • readOnlyHint: false
  • settle_evaluationConfirm that an ALLOWed payment settled.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
    Confirm that an ALLOWed payment settled. Requires the evaluation_id and the reservation_token returned by evaluate_payment, plus the real transaction/hash reference. Idempotent for the same evaluation; never call this before settlement.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: false
Only reads 7Show 7 read-only tools
  • get_audit_trailView recent payment-approval audit records for an ownerNo findings

    Why it is in this group

    • The name "get_audit_trail" says "get": a word for reading.
    Description, as the server wrote it
    View recent payment-approval audit records for an owner

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
  • get_evaluationInspect the reservation/settlement state of an evaluationNo findings

    Why it is in this group

    • The name "get_evaluation" says "get": a word for reading.
    Description, as the server wrote it
    Inspect the reservation/settlement state of an evaluation

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
  • get_policyView the active signed payment policy for an owner (and optionally an agent scope)No findings

    Why it is in this group

    • The name "get_policy" says "get": a word for reading.
    Description, as the server wrote it
    View the active signed payment policy for an owner (and optionally an agent scope)

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
  • get_policy_versionsView a user's policy version history (version chain + hashes, verifiable against on-chain commitments)No findings

    Why it is in this group

    • The name "get_policy_versions" says "get": a word for reading.
    Description, as the server wrote it
    View a user's policy version history (version chain + hashes, verifiable against on-chain commitments)

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
  • get_spend_reportView today's spend summary for an ownerNo findings

    Why it is in this group

    • The name "get_spend_report" says "get": a word for reading.
    Description, as the server wrote it
    View today's spend summary for an owner

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
  • list_policy_requestsList pending agent policy-change requestsNo findings

    Why it is in this group

    • The name "list_policy_requests" says "list": a word for reading.
    Description, as the server wrote it
    List pending agent policy-change requests

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
  • list_templatesList policy templates (personal assistant / travel / dev API / procurement)No findings

    Why it is in this group

    • The name "list_templates" says "list": a word for reading.
    Description, as the server wrote it
    List policy templates (personal assistant / travel / dev API / procurement)

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: 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 or untrusted-input.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write0
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out1
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 21, 2026, 19:24 UTC, unchanged since Nov 7, 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
7
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 7 tools that change things (1 destructive, 1 irreversible, 5 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://api.boundra.io/mcp: tools/list returned 14 tools to an anonymous client, including revoke_policy (destructive), evaluate_payment (irreversible), settle_evaluation (write), release_evaluation (write), request_policy_change (write) and 2 more

    What this check looks for

Posture changes

  1. Nov 7, 2026
    • Tools that change things, listed without credentials: 5 to 7

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

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

  1. Tools14 changed.~14 changedView diff
  2. Tools3 added, 1 changed.+3 added~1 changedView diff
  3. PostureRemote posture changed. Tools that change things, listed without credentials: 5 -> 7.View diff
    • Tools that change things, listed without credentials: 5 to 7

Install

Pinned to version 0.2.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http boundra https://api.boundra.io/mcp
claude mcp add --transport http boundra https://api.boundra.io/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__boundra__get_evaluation",
      "mcp__boundra__get_policy",
      "mcp__boundra__get_spend_report",
      "mcp__boundra__get_audit_trail",
      "mcp__boundra__get_policy_versions",
      "mcp__boundra__list_policy_requests",
      "mcp__boundra__list_templates"
    ],
    "ask": [
      "mcp__boundra__evaluate_payment",
      "mcp__boundra__settle_evaluation",
      "mcp__boundra__release_evaluation",
      "mcp__boundra__request_policy_change",
      "mcp__boundra__set_policy",
      "mcp__boundra__render_template"
    ],
    "deny": [
      "mcp__boundra__revoke_policy"
    ]
  }
}

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 boundra. Review it before you use it.

Capability tags behind 1 rule
  • mcp__boundra__evaluate_payment 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/io.boundra/boundra/verify?hash=fb8394f359a8efb597d0b048545d57df3e3187d0e94e7578bca5a5deb923071a" | jq -e '.changed == false'

Pinned hash fb8394f359a8, from Nov 10, 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/io.boundra/boundra/changes.xml

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

Badge

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

Source: MCP Registry · repository. Synced Nov 10, 2026, 07:17 UTC.

Boundra — Payment Approval Gateway for AI Agents MCP server: questions and answers

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

Is the Boundra — Payment Approval Gateway for AI Agents MCP server safe?

No scan can promise that. What its definitions show: 14 tools, 7 of which can change, send or delete something, and 0 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 Boundra — Payment Approval Gateway for AI Agents MCP server delete data?

Yes. 1 tool can delete, cancel or revoke something: revoke_policy.

Can the Boundra — Payment Approval Gateway for AI Agents MCP server do things that cannot be undone?

Yes. 1 tool can send, pay, publish or merge: evaluate_payment.

What tools does the Boundra — Payment Approval Gateway for AI Agents MCP server have?

14 tools: 1 destructive, 1 irreversible, 5 write, 7 read. revoke_policy, evaluate_payment, settle_evaluation, release_evaluation, request_policy_change, set_policy, render_template, get_evaluation and 6 more.

Does the Boundra — Payment Approval Gateway for AI Agents MCP server need sign-in or OAuth?

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

Does the Boundra — Payment Approval Gateway for AI Agents MCP server send data to outside services?

1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): evaluate_payment.

Has the Boundra — Payment Approval Gateway for AI Agents MCP server changed its tools?

Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 10, 2026. Every change is on this page and in its Atom feed.