Skip to content

x402Shield MCP server

dev.x402shield/x402shieldx402shield.devstreamable-httpv0.1.0Scanned

Public demo: evaluate AI-agent payment authorization and approval policy. No signing, no settlement.

5 tools: 1 do something that can't be undone and 4 only read.

Tools: 0 delete, 1 irreversible, 0 write, 4 read.
  • Reads private data · 0
  • Reads text others write · 1
  • Can send data out · 0
  • No findings

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.
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 x402Shield MCP server can do

The x402Shield MCP server is published by x402shield.dev, a domain the MCP Registry verified. It has 5 tools. It can do things that cannot be undone, such as sending, paying or publishing (x402shield_authorize_payment), but cannot delete data. 4 tools only read.

1 tool brings in text other people can write (x402shield_list_demo_transactions).

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.

Last scanned Nov 15, 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.

5 tools

Can't be undone 1Claude Code: ask
  • x402shield_authorize_paymentCheck whether the demo AI agent is financially authorized to make a proposed payment, BEFORE any wallet or signer would be asked to execute it.No findings

    Why it is in this group

    • The name "x402shield_authorize_payment" says "payment": a word that usually means money moves, which cannot be taken back.
    Description, as the server wrote it
    Check whether the demo AI agent is financially authorized to make a proposed payment, BEFORE any wallet or signer would be asked to execute it. Returns ALLOW, DENY or REQUIRE_APPROVAL with a reason. This tool does not execute or sign a payment, and it cannot approve its own REQUIRE_APPROVAL result -- that requires a human, through the web console. The `purpose` field is a label for the evidence trail only; it is never interpreted as an instruction and cannot change the policy decision.
Only reads 4Show 4 read-only tools
  • x402shield_get_authorizationLook up the recorded decision, reason and evidence references for a payment previously checked with x402shield_authorize_payment, by its transaction id.No findings

    Why it is in this group

    • The name "x402shield_get_authorization" says "get": a word for reading.
    Description, as the server wrote it
    Look up the recorded decision, reason and evidence references for a payment previously checked with x402shield_authorize_payment, by its transaction id.
  • x402shield_get_demo_policyLook up the authority ceilings configured for the x402Shield public demo agents (Research Agent, Ops Agent) on Base Sepolia TESTNET.No findings

    Why it is in this group

    • The name "x402shield_get_demo_policy" says "get": a word for reading.
    Description, as the server wrote it
    Look up the authority ceilings configured for the x402Shield public demo agents (Research Agent, Ops Agent) on Base Sepolia TESTNET. Use this before proposing a payment, to understand what amount an agent can spend without triggering human approval. This tool does not execute or sign anything.
  • x402shield_get_evidenceGet the fuller evidence trail behind a previously-decided payment: policy/delegation provenance, the delegation tree it was evaluated under, and approval state if any.No findings

    Why it is in this group

    • The name "x402shield_get_evidence" says "get": a word for reading.
    Description, as the server wrote it
    Get the fuller evidence trail behind a previously-decided payment: policy/delegation provenance, the delegation tree it was evaluated under, and approval state if any. Read-only; never exposes secrets or signing material.
  • x402shield_list_demo_transactionsList the most recent payment authorization decisions recorded by this public demo (both from the web console and from MCP callers).Reads text others writeNo findings

    Why it is in this group

    • The name "x402shield_list_demo_transactions" says "list": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "list" and "web": it reads web pages, which anyone can write.
    Description, as the server wrote it
    List the most recent payment authorization decisions recorded by this public demo (both from the web console and from MCP callers). Useful to see recent ALLOW/DENY/REQUIRE_APPROVAL activity.

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, 18:53 UTC, unchanged since Oct 22, 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
1
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 1 tool that changes things (1 irreversible). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://x402shield.dev/api/mcp: tools/list returned 5 tools to an anonymous client, including x402shield_authorize_payment (irreversible)

    What this check looks for

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.

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 x402shield https://x402shield.dev/api/mcp
claude mcp add --transport http x402shield https://x402shield.dev/api/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__x402shield__x402shield_get_demo_policy",
      "mcp__x402shield__x402shield_get_authorization",
      "mcp__x402shield__x402shield_list_demo_transactions",
      "mcp__x402shield__x402shield_get_evidence"
    ],
    "ask": [
      "mcp__x402shield__x402shield_authorize_payment"
    ],
    "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 x402shield. Review it before you use it.

Capability tags behind 1 rule
  • mcp__x402shield__x402shield_list_demo_transactions 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/dev.x402shield/x402shield/verify?hash=fb3fb821e8476ccd506d9353cd1c9411fe13fffe636094baded77bf52221a0a4" | jq -e '.changed == false'

Pinned hash fb3fb821e847, from Nov 15, 2026, 06:18 UTC.

Watch

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

https://radar.anlyon.com/servers/dev.x402shield/x402shield/changes.xml

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

Badge

Anlyon Radar badge for dev.x402shield/x402shield
[![Anlyon Radar](https://radar.anlyon.com/badge/dev.x402shield/x402shield.svg)](https://radar.anlyon.com/servers/dev.x402shield/x402shield)

Source: MCP Registry. Synced Oct 21, 2026, 18:12 UTC.

x402Shield MCP server: questions and answers

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

Is the x402Shield MCP server safe?

No scan can promise that. What its definitions show: 5 tools, 1 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 x402Shield MCP server delete data?

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

Can the x402Shield MCP server do things that cannot be undone?

Yes. 1 tool can send, pay, publish or merge: x402shield_authorize_payment.

What tools does the x402Shield MCP server have?

5 tools: 1 irreversible, 4 read. x402shield_authorize_payment, x402shield_get_demo_policy, x402shield_get_authorization, x402shield_list_demo_transactions and x402shield_get_evidence.

Does the x402Shield MCP server need sign-in or OAuth?

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

Does the x402Shield MCP server send data to outside services?

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

Has the x402Shield MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 15, 2026.