# contextboundary-gw

> contextboundary-gw — kannanokannan-contextboundary-gw. Use this tool when you need to enforce secure and transparent policy decisions for tool discovery and data flow, ensuring deterministic outcomes and verifiable receipts. It solves problems related to secure data exchange, compliance, and auditability by applying compiled policy to outbound data flow. The contextboundary-gw gateway takes in policy inputs and emits hash-chained receipts with Ed25519 signatures, making it ideal for use cases requiring high security and accountability.

Canonical page: https://skillsregistry.net/skills/kannanokannan-contextboundary-gw  
JSON: https://api.skillsregistry.net/v1/skills/kannanokannan-contextboundary-gw

## Description

Self-hosted MCP gateway that applies deterministic, compiled policy to tool discovery, invocation, and outbound data flow, with no model in the enforcement path. Every decision emits a hash-chained receipt sealed with Ed25519 and verifiable using public keys only.

## Trust

- **Trust score (0–1):** 0.48
- **Verification tier:** scanned
- **Last scanned:** 2026-08-29

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** other
- **Updated:** 2026-08-29

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/bo47jh5ggz)
- **Repository:** <https://github.com/kannanokannan/contextboundary-gw>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "kannanokannan-contextboundary-gw"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/kannanokannan-contextboundary-gw` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/kannanokannan-contextboundary-gw/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt