REDHAND.
INSTRUMENT 04 // SECURE04 — AI AGENT SECURITY & CONTROL LAYER · MCP GATEWAY
Identify every agent, control what it touches, and stop it in seconds.
RedHand sits inline between your connected AI agents and their MCP tool servers. It enforces short-lived Ed25519 Agent Passports, read/write tool scopes, Organization Safe Mode, daily Budget Guard caps, planted honeytokens, SHA-256 tool pinning, and a tamper-evident Black Box timeline—with zero LLM calls on the hot path.
Covers agents connected via the RedHand gateway (n8n, Claude, LangGraph, CrewAI, custom). Includes 10-min Ed25519 tokens, Telegram /freeze_all, SHA-256 Black Box, Honeytokens, and MCP Tool Pinning.
01 — INTERACTIVE GATEWAY & CONTROL SIMULATOR
Inspect how RedHand enforces Phases 1–4 inline.
// JSON-RPC tools/call via AgentWall MCP Gateway (:8080)
{
"method": "tools/call",
"params": {
"name": "postgres_prod.execute_sql",
"arguments": {
"query": "DROP TABLE retail_ledger_transactions CASCADE;"
}
}
}gate: agentwall/src/gateway/service.py + ast_guardrails.py
passport_token: Ed25519 JWT (ttl <= 600s, status: "active")
org_safe_mode: true (read-only enforced across organization)
sqlglot_ast: DDL_DESTRUCTIVE ("DROP") + scope "write" not in passportRefused fail-closed before reaching the upstream MCP server. Recorded in the organization's SHA-256 Black Box timeline with reason `safe_mode` / `out_of_scope`.
02 — BUILT & VERIFIED CAPABILITIES
Six deterministic control layers.
RedHand only controls and sees what flows through the RedHand gateway, or what an owner submits to the scanner.
Ed25519 Agent Passports & Inline MCP Gateway
Registers every agent (n8n, Claude, LangGraph, CrewAI, custom) with owner, backup owner, server/tool read-write scopes, expiry, and 10-minute Ed25519 tokens enforced at the fail-closed AgentWall proxy.
Kill Switch, Safe Mode & Telegram /freeze_all
Freeze or permanently revoke a single agent, flip the organization into read-only Safe Mode, or send /freeze_all from Telegram on your phone to stop every connected agent within 5 seconds.
Budget Guard & Daily Tool-Call Caps
Enforces per-agent and organization-default daily tool-call limits with non-blocking in-memory metering, instant Telegram breach alerts, and opt-in automatic agent freeze.
SHA-256 Hash-Chained Black Box & DLP Capture
Per-organization append-only timeline of every allowed, refused, or failed tools/call with one-click chain Verify, JSONL/CSV export, and opt-in 2 KB payload capture that redacts secrets, emails, cards, and Malaysian NRICs.
Planted Honeytokens & Decoy MCP Tools
Issues bait credentials (sk_live_…, AKIA…, passwords stored only as SHA-256 digests) and per-agent decoy tools in tools/list. Any touch is refused before upstream, alerts Telegram in < 10s, and freezes the agent.
Bilingual MCP Scanner & SHA-256 Tool Pinning
Scans pasted manifests or live registered MCP servers (English & Bahasa Malaysia rules, measured by redhand bench) and pins SHA-256 tool hashes on tools/list to stop post-approval rug pulls.
Manage your connected agents in the RedHand Console.
Agent Passports
Register agents, edit server/tool read-write scopes, toggle Safe Mode, set Budget Guard caps, or trigger Freeze All.
Black Box Recorder
Inspect the append-only timeline, run cryptographic SHA-256 chain verification, manage DLP payload capture, and export JSONL/CSV.
Honeytokens & Decoys
Plant one-time API/AWS/password bait tokens and per-agent decoy MCP tools with automatic freeze and Telegram alerts.
MCP Scanner & Tool Pins
Vet MCP manifests or scan live registered servers for hidden EN/BM instructions, and approve or reject SHA-256 tool pins.