# Tkach Security MCP server

> Provides a fail-closed security boundary that authorizes AI agent actions and controls data flow through a Rust-based runtime.

- Repository: https://github.com/ECD5A/Tkach-Security
- Page: https://hostedmcp.org/servers/ecd5a/tkach-security
- Transport: stdio
- Stars: 1
- License: Apache-2.0
- Latest version: 0.1.2

## Environment variables

| Name | Required | Secret | Description |
|---|---|---|---|
| `TKACH_BEARER_TOKEN` | yes | yes | Trusted bearer proof for the local runtime. |
| `TKACH_HTTP_ADDR` | no | no | Loopback address of the already running Tkach HTTP runtime. |

## FAQ

### What does Tkach Security protect against?

It acts as a security boundary for AI agents, ensuring that even if a model is compromised, its output remains untrusted and actions must be explicitly authorized.

### How does Tkach handle permissions for actions?

Protected actions require an exact-scope, Core-issued 'Propusk' which cannot be created by model text alone.

### Does Tkach detect prompt injections?

No, Tkach does not claim to detect every prompt injection or make the model itself trustworthy.

### Can I use Tkach without a Rust toolchain?

Yes, you can download a binary to start with the 'tkach init' command.
