Web3 & AI Firewall: EIP-7702 hijacks, Solana Token-2022 drainers, EVM tx & MCP injection check.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Instant triage audit of Solidity contracts or MCP/AI agent configs for vulnerabilities & token burn.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http chainguard-shield https://chainguard-studio-production.up.railway.app/mcp
Instant triage audit of Solidity contracts or MCP/AI agent configs for vulnerabilities & token burn.
| Argument | Type | Description |
|---|---|---|
| content* | string | |
| target_type | string |
{
"type": "object",
"required": [
"content"
],
"properties": {
"content": {
"type": "string"
},
"target_type": {
"type": "string",
"default": "auto"
}
}
}Detect active EIP-7702 EOA delegation hijacks (0xef0100...) on Ethereum, Base, Arbitrum, or Polygon.
| Argument | Type | Description |
|---|---|---|
| address* | string | |
| network | string |
{
"type": "object",
"required": [
"address"
],
"properties": {
"address": {
"type": "string"
},
"network": {
"type": "string",
"default": "base"
}
}
}Detect hidden zero-width Unicode smuggling & prompt injection inside MCP tools or web text.
| Argument | Type | Description |
|---|---|---|
| text* | string |
{
"type": "object",
"required": [
"text"
],
"properties": {
"text": {
"type": "string"
}
}
}Inspect Solana SPL / Token-2022 mint for PermanentDelegate drainers, TransferHooks, Mint/Freeze authority & RugCheck score.
| Argument | Type | Description |
|---|---|---|
| mint* | string |
{
"type": "object",
"required": [
"mint"
],
"properties": {
"mint": {
"type": "string"
}
}
}Pre-flight EVM transaction drainer & unlimited approval firewall (Base/Arbitrum/Polygon).
| Argument | Type | Description |
|---|---|---|
| to* | string | |
| network | string | |
| calldata | string |
{
"type": "object",
"required": [
"to"
],
"properties": {
"to": {
"type": "string"
},
"network": {
"type": "string",
"default": "base"
},
"calldata": {
"type": "string",
"default": "0x"
}
}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 20, 2026.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.