Skip to content

Address Poisoning Check MCP server

io.github.devx-agent/address-poisoning-checkdevx-agentstreamable-httpv1.1.0Scanned

Before sending crypto, check the recipient for address poisoning: lookalikes and bad checksums

2 tools: 1 do something that can't be undone and 1 change things.

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

Sign-in required, no OAuth metadata. 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 Address Poisoning Check MCP server can do

The Address Poisoning Check MCP server is published by the GitHub account devx-agent. It has 2 tools. It can do things that cannot be undone, such as sending, paying or publishing (check_recipient_lookalike) and create or change data (1 tool: onchain_check_info), but cannot delete data. None of its tools only reads.

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

The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.

Last scanned Nov 12, 2026, version 1.1.0.

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.

2 tools

Can't be undone 1Claude Code: ask
  • check_recipient_lookalikeFree, offline, read-only: before sending crypto, check whether the recipient address is a lookalike (same first/last hex characters, different middle) of any address you trust, and…Can send data out1 finding

    Why it is in this group

    • The input addresses people (input.to): what it sends cannot be taken back.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • outboundThe input takes a destination (input.to): what the tool writes goes there.

    Findings

    • Warn

      The server marks "check_recipient_lookalike" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".

      Matched text

      annotations: {"readOnlyHint":true,"openWorldHint":false}; The input addresses people (input.to): what it sends cannot be taken back.

      What this check looks for
    Description, as the server wrote it
    Free, offline, read-only: before sending crypto, check whether the recipient address is a lookalike (same first/last hex characters, different middle) of any address you trust, and whether its EIP-55 checksum is valid. Address poisoning stole $76M+ in 12 months by planting such lookalikes in wallet histories.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
Changes things 1Claude Code: ask
  • onchain_check_infoHow to buy the on-chain check (scans the sender's real transfer history on Ethereum/Base/Avalanche for poisoning transfers and lookalikes) via x402 for 0.005 USDC.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
    How to buy the on-chain check (scans the sender's real transfer history on Ethereum/Base/Avalanche for poisoning transfers and lookalikes) via x402 for 0.005 USDC. Does not pay.

    Annotations the server declares

    • 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.

Sign-in required, no OAuth metadata

Looked at Nov 21, 2026, 19:23 UTC, unchanged since Nov 21, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
404
tools/list served without credentials
no
Tools that change things, listed without credentials
0
Protocol version
not observed
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

The probe stopped: initialize answered HTTP 404.

Posture changes

  1. Nov 21, 2026
    • HTTP status of an anonymous initialize: 200 to 404
    • tools/list served without credentials: yes to no
    • Tools that change things, listed without credentials: 2 to 0
    • Protocol version: 2025-06-18 to none

Findings

Matches of fixed checks, with the text they matched.

1 warn
  • The server marks "check_recipient_lookalike" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".

    Matched text

    annotations: {"readOnlyHint":true,"openWorldHint":false}; The input addresses people (input.to): what it sends cannot be taken back.

    What this check looks for

History

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

  1. PostureRemote posture changed. HTTP status of an anonymous initialize: 200 -> 404; tools/list served without credentials: yes -> no; Tools that change things, listed without credentials: 2 -> 0 (and 1 more).View diff
    • HTTP status of an anonymous initialize: 200 to 404
    • tools/list served without credentials: yes to no
    • Tools that change things, listed without credentials: 2 to 0
    • Protocol version: 2025-06-18 to none

Install

Pinned to version 1.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http address-poisoning-check https://address-poisoning-check.nextill-pos.workers.dev/mcp
claude mcp add --transport http address-poisoning-check https://address-poisoning-check.nextill-pos.workers.dev/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": [],
    "ask": [
      "mcp__address-poisoning-check__check_recipient_lookalike",
      "mcp__address-poisoning-check__onchain_check_info"
    ],
    "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 address-poisoning-check. Review it before you use it.

Capability tags behind 1 rule
  • mcp__address-poisoning-check__check_recipient_lookalike 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.github.devx-agent/address-poisoning-check/verify?hash=5f799386ecb2035964ee4466b4b54d783e291ce04f155488ab2d2df6325077a9" | jq -e '.changed == false'

Pinned hash 5f799386ecb2, from Nov 12, 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.devx-agent/address-poisoning-check/changes.xml

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

Badge

Anlyon Radar badge for io.github.devx-agent/address-poisoning-check
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.devx-agent/address-poisoning-check.svg)](https://radar.anlyon.com/servers/io.github.devx-agent/address-poisoning-check)

Source: MCP Registry · repository. Synced Oct 30, 2026, 21:17 UTC.

Address Poisoning Check MCP server: questions and answers

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

Is the Address Poisoning Check MCP server safe?

No scan can promise that. What its definitions show: 2 tools, 2 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the Address Poisoning Check MCP server delete data?

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

Can the Address Poisoning Check MCP server do things that cannot be undone?

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

What tools does the Address Poisoning Check MCP server have?

2 tools: 1 irreversible, 1 write. check_recipient_lookalike and onchain_check_info.

Does the Address Poisoning Check MCP server need sign-in or OAuth?

Its remote endpoint did not answer the last anonymous look.

Does the Address Poisoning Check 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): check_recipient_lookalike.

Has the Address Poisoning Check MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 12, 2026.