Agent Trust Firewall

Name: Agent Trust Firewall
Author: Benji18sport

MCP serverMCP

Free pre-action policy checks and data cleaning for autonomous AI agents.

by Benji18sportrepository ↗v1.8.1

Is this yours?

This record is unclaimed

Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.

Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"agent-trust-firewall","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.

Claim this record

Observed by Wellknown

Evidence

Everything here was measured by our prober or read from a registry. Nothing is self-reported.

30-day availability7/7 checks ok

30 days ago

when	check	result	http	latency	detail
3 h ago	mcp initialize	ok	200	31 ms	server agent-trust-firewall 1.8.1 · protocol 2025-06-18 · 5 tools
12 h ago	mcp initialize	ok	200	57 ms	server agent-trust-firewall 1.8.1 · protocol 2025-06-18 · 5 tools
20 h ago	mcp initialize	ok	200	71 ms	server agent-trust-firewall 1.8.1 · protocol 2025-06-18 · 5 tools
28 h ago	mcp initialize	ok	200	45 ms	server agent-trust-firewall 1.8.1 · protocol 2025-06-18 · 5 tools
2 d ago	mcp initialize	ok	200	151 ms	server agent-trust-firewall 1.8.1 · protocol 2025-06-18 · 5 tools
2 d ago	mcp initialize	ok	200	36 ms	server agent-trust-firewall 1.8.1 · protocol 2025-06-18 · 5 tools
2 d ago	mcp initialize	ok	200	27 ms	server agent-trust-firewall 1.8.1 · protocol 2025-06-18 · 5 tools

Tools observed via MCP handshake

trust_check_action — Evaluate a proposed action against evidence, source allowlists, data constraints and payment limits, returning ALLOW/BLOCK with reason codes. All enabled checks
trust_check_spend — Compare a proposed spend with a remaining budget, transaction ceiling and merchant allowlist, returning ALLOW/BLOCK with reasons. Budget and ceiling are indepen
trust_validate_data — Validate JSON field presence, exact types, primitive enums and inclusive numeric bounds, returning ALLOW/BLOCK, field reasons and checked_fields. Combine requir
trust_clean_data — Audit and optionally clean up to 500 JSON rows, returning cleaned_rows, original zero-based issues and counts. Processing order is trim, primary-key deduplicati
trust_get_capabilities — Discover the deployed version, request/row limits, tool names, legacy call aliases and check-clean-recheck workflow before integrating. Pass {}: this inventory

Declared by sources

What the publisher says

Attributed to the source that supplied each field. Treated as claims, not facts.

No long description beyond the summary.

kind Official MCP Registry

name Official MCP Registry

repoUrl Official MCP Registry

summary Official MCP Registry

version Official MCP Registry

description Official MCP Registry

publisherName Official MCP Registry

Provenance

Where this record came from

Every source is kept verbatim. Field changes are logged as events.

Official MCP Registryio.github.Benji18sport/agent-trust-firewall

first seen 2 d ago · fetched 2 d agoopen ↗

Field history (6 recent events)

2 d ago · declared · summary → "Free pre-action policy checks and data cleaning for autonomous AI agents."
2 d ago · declared · description → "Free pre-action policy checks and data cleaning for autonomous AI agents."
2 d ago · declared · publisherName → "Benji18sport"
2 d ago · declared · repoUrl → "https://github.com/Benji18sport/agent-commerce-os"
2 d ago · declared · version → "1.5.0"
2 d ago · declared · protocols → ["mcp"]

This record is unclaimed

Evidence

What the publisher says

Capabilities

Where this record came from