# Policy Firewall

> Use this tool when you need to enforce security and governance policies for AI clients accessing downstream servers, to intercept and evaluate tool call requests against configurable rules and constraints. It solves problems of unauthorized access, sensitive data exposure, and unregulated tool usage, providing a secure interface for AI clients to interact with MCP servers. It takes in tool call requests and policy rules as inputs, and returns allow/deny decisions with structured explanations as outputs.

Canonical page: https://skillsregistry.net/skills/nhpsecurity-policy-firewall  
JSON: https://api.skillsregistry.net/v1/skills/nhpsecurity-policy-firewall

## Description

Policy Firewall sits as middleware between AI clients and downstream MCP servers, intercepting tool call requests before execution. It evaluates configurable JSON policy rules with allowlist/denylist patterns, enforces path and domain scope constraints, requires confirmation for sensitive operations, redacts secrets from audit logs, and returns structured denial explanations to the AI client. Supports filesystem, git, and network tool governance.

## Trust

- **Trust score (0–1):** 0.87
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** security
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/nhpsecurity-policy-firewall)
- **Repository:** <https://github.com/nhpsecurity/mcp-policy-firewall>

## 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": "nhpsecurity-policy-firewall"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/nhpsecurity-policy-firewall` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/nhpsecurity-policy-firewall/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