Skip to content

ChainGuard Web3 & MCP Shield

app.railway.up.chainguard-studio-production/chainguard-shieldchainguard-studio-production.up.railway.appstreamable-httpv1.0.0Scanned

Web3 & AI Firewall: EIP-7702 hijacks, Solana Token-2022 drainers, EVM tx & MCP injection check.

5 tools: 1 do something that can't be undone, 3 change things and 1 only read.

Tools: 0 delete, 1 irreversible, 3 write, 1 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 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 ChainGuard Web3 & MCP Shield can do

The ChainGuard Web3 & MCP Shield is published by chainguard-studio-production.up.railway.app, a domain the MCP Registry verified. It has 5 tools. It can do things that cannot be undone, such as sending, paying or publishing (check_tx_firewall) and create or change data (3 tools: check_eip7702_delegation, check_mcp_poisoning and audit_solidity_or_mcp), but cannot delete data. 1 tool only reads.

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

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 20, 2026, version 1.0.0.

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
  • check_tx_firewallPre-flight EVM transaction drainer & unlimited approval firewall (Base/Arbitrum/Polygon).Can send data outNo findings

    Why it is in this group

    • The input addresses people (input.to): what it sends cannot be taken back.

    What it can reach

    • outboundThe input takes a destination (input.to): what the tool writes goes there.
    Description, as the server wrote it
    Pre-flight EVM transaction drainer & unlimited approval firewall (Base/Arbitrum/Polygon).
Changes things 3Claude Code: ask
  • audit_solidity_or_mcpInstant triage audit of Solidity contracts or MCP/AI agent configs for vulnerabilities & token burn.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
    Instant triage audit of Solidity contracts or MCP/AI agent configs for vulnerabilities & token burn.
  • check_eip7702_delegationDetect active EIP-7702 EOA delegation hijacks (0xef0100...) on Ethereum, Base, Arbitrum, or Polygon.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
    Detect active EIP-7702 EOA delegation hijacks (0xef0100...) on Ethereum, Base, Arbitrum, or Polygon.
  • check_mcp_poisoningDetect hidden zero-width Unicode smuggling & prompt injection inside MCP tools or web text.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
    Detect hidden zero-width Unicode smuggling & prompt injection inside MCP tools or web text.
Only reads 1Show 1 read-only tool
  • check_solana_token2022Inspect Solana SPL / Token-2022 mint for PermanentDelegate drainers, TransferHooks, Mint/Freeze authority & RugCheck score.No findings

    Why it is in this group

    • The description's first verb is "inspect": a word for reading.
    Description, as the server wrote it
    Inspect Solana SPL / Token-2022 mint for PermanentDelegate drainers, TransferHooks, Mint/Freeze authority & RugCheck score.

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 20, 2026, 18:18 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
4
Protocol version
2024-11-05
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 4 tools that change things (1 irreversible, 3 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://chainguard-studio-production.up.railway.app/mcp: tools/list returned 5 tools to an anonymous client, including check_tx_firewall (irreversible), check_eip7702_delegation (write), check_mcp_poisoning (write), audit_solidity_or_mcp (write)

    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 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http chainguard-shield https://chainguard-studio-production.up.railway.app/mcp
claude mcp add --transport http chainguard-shield https://chainguard-studio-production.up.railway.app/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__chainguard-shield__check_solana_token2022"
    ],
    "ask": [
      "mcp__chainguard-shield__check_eip7702_delegation",
      "mcp__chainguard-shield__check_tx_firewall",
      "mcp__chainguard-shield__check_mcp_poisoning",
      "mcp__chainguard-shield__audit_solidity_or_mcp"
    ],
    "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 chainguard-shield. Review it before you use it.

Capability tags behind 1 rule
  • mcp__chainguard-shield__check_tx_firewall 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/app.railway.up.chainguard-studio-production/chainguard-shield/verify?hash=b321eda5c14a8901b04f0b2fd87277e1fd57af36b85722f04c3cd6e924723d90" | jq -e '.changed == false'

Pinned hash b321eda5c14a, from Nov 20, 2026, 16:18 UTC.

Watch

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

https://radar.anlyon.com/servers/app.railway.up.chainguard-studio-production/chainguard-shield/changes.xml

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

Badge

Anlyon Radar badge for app.railway.up.chainguard-studio-production/chainguard-shield
[![Anlyon Radar](https://radar.anlyon.com/badge/app.railway.up.chainguard-studio-production/chainguard-shield.svg)](https://radar.anlyon.com/servers/app.railway.up.chainguard-studio-production/chainguard-shield)

Source: MCP Registry. Synced Nov 20, 2026, 16:17 UTC.

ChainGuard Web3 & MCP Shield: questions and answers

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

Is the ChainGuard Web3 & MCP Shield safe?

No scan can promise that. What its definitions show: 5 tools, 4 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 ChainGuard Web3 & MCP Shield delete data?

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

Can the ChainGuard Web3 & MCP Shield do things that cannot be undone?

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

What tools does the ChainGuard Web3 & MCP Shield have?

5 tools: 1 irreversible, 3 write, 1 read. check_tx_firewall, check_eip7702_delegation, check_mcp_poisoning, audit_solidity_or_mcp and check_solana_token2022.

Does the ChainGuard Web3 & MCP Shield need sign-in or OAuth?

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

Does the ChainGuard Web3 & MCP Shield send data to outside services?

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

Has the ChainGuard Web3 & MCP Shield changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 20, 2026.