mastyf-ai/mastyf.ai

Secure the Action Boundary, Not Just the Prompt.
A local reference monitor and security gateway for AI agents and MCP. Your LLM proposes actions. Mastyf decides whether those actions reach the real world.
Website ·
Quick start ·
Policy ·
Dashboard ·
GitHub
> [!NOTE]
> **Enterprise & Cloud Platform Support:** Mastyf is verified and deployed as a native CONTENT_AUTHZ Service Extension for **Google Cloud Agent Gateway** (us-central1), with distributed Redis state, sub-second fail-closed enforcement, and real-time BigQuery audit logging. See the Google Agent Gateway Runbook.
---
The problem
AI agents can read your files, push code, query databases, execute shell commands, and call external APIs. They do it autonomously, at machine speed.
Traditional security controls weren't built for that.
Mastyf.ai acts as a perimeter security layer for AI. It intercepts every tool call, evaluates it against your security policies using multi-agent swarm analysis, and blocks malicious or unauthorized actions before they execute.
Every decision is enforced, logged, and auditable.
---
What it stops
| Threat | What it looks like |
|--------|--------------------|
| Prompt injection | Malicious instructions embedded in tool arguments to hijack agent behavior |
| Path traversal | Attempts to access /etc/passwd, .ssh/id_rsa, .aws/credentials |
| Secret exfiltration | API keys and tokens leaking through tool arguments |
| Shell injection | Reverse shells, rm -rf, encoded PowerShell commands |
| Data exfiltration | Bulk SQL dumps, git push, aws s3 cp, unauthorized file transfers |
| SSRF | Calls to metadata endpoints, localhost, and private IP ranges |
| Encoding evasion | Base64 blobs and Unicode homoglyphs used to bypass pattern detection |
| Cost abuse | Runaway agent loops burning through token budgets |
| Rug-pull attacks | Tool definitions that silently change mid-session |
---
Quick start
🛡️ Mastyf Security Gateway & Protected Agent (Python Quickstart)
Run the local reference monitor, MCP discovery, and plain-English protected agent runtime:
* On first run, Mastyf automatically discovers your local MCP servers/tools, prompts for your intended permissions in plain English, presents a conservative diff, and upon confirmation activates the policy.
* Every tool proposal from the conversational agent is intercepted by the reference monitor ($A = \text{CBAC} \cap \text{DIFC} \cap \text{Workflow}$). Non-ALLOW actions dispatch **strictly 0 bytes** to tool backends.
* Includes real-time **Security HUD** and cryptographic receipt audit chaining (mastyf audit verify).
Common CLI Commands
---
Build from source (TypeScript / Cloud Platform)
Clone the repository and run the setup script.
**Requirements:**
- Git
- Linux (the setup script installs Nix automatically if needed)
The setup script automatically:
- Installs Nix (if required)
- Enables Nix flakes
- Creates the development environment
- Installs all project dependencies
- Rebuilds native packages
- Builds the entire project
- Adds a convenient mastyf shell alias
Once installation completes, start the proxy and dashboard:
Or simply use the alias after opening a new terminal:
The dashboard will be available at:
- Dashboard: http://localhost:4000
---
Test the installation
If the dashboard is running, verify the HTTP bridge:
---
Dashboard
Full visibility into every action your AI takes.
---
| Section | What you see |
|---------|-------------|
| Protection | Block rate, top triggered rules, live threat feed |
| Activity | Every tool call with full arguments, allow or block status, timestamp |
| Policy | Live rule editor with hot-reload from YAML |
| Threat Lab | AI-suggested attack tests, reviewed and approved before anything applies |
| Cost | Token usage and cost estimates broken down per tool call |