Free pre-action policy checks and data cleaning for autonomous AI agents.
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.
Data Cleaner — deterministic advisory policy or data processing. Free pilot. Caller must enforce BLOCK.
This tool takes no arguments.
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.
claude mcp add --transport http agent-trust-firewall https://agent-trust-firewall.andrea-vignoni.workers.dev/mcp
Data Cleaner — deterministic advisory policy or data processing. Free pilot. Caller must enforce BLOCK.
No arguments.
{
"type": "object",
"additionalProperties": true
}Agent Trust Firewall — deterministic advisory policy or data processing. Free pilot. Caller must enforce BLOCK.
No arguments.
{
"type": "object",
"additionalProperties": true
}Agent Trust Spend Guard — deterministic advisory policy or data processing. Free pilot. Caller must enforce BLOCK.
No arguments.
{
"type": "object",
"additionalProperties": true
}Agent Trust Validate — deterministic advisory policy or data processing. Free pilot. Caller must enforce BLOCK.
No arguments.
{
"type": "object",
"additionalProperties": true
}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 Oct 30, 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.