# mcpwall

> Use this tool when you need to secure and control MCP tool calls with customizable policies. It intercepts and enforces YAML-defined rules on every JSON-RPC request between the client and server, solving security and access control problems. Ideal for use cases requiring fine-grained control over MCP interactions, with inputs including JSON-RPC requests and YAML policy files, and outputs being allowed or blocked requests.

Canonical page: https://skillsregistry.net/skills/behrensd-mcpwall  
JSON: https://api.skillsregistry.net/v1/skills/behrensd-mcpwall

## Description

mcpwall is a deterministic security proxy for MCP tool calls — iptables for MCP.
It sits between the MCP client and server, intercepting every JSON-RPC request and enforcing YAML-defined policies.

## Trust

- **Trust score (0–1):** 0.60
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** security
- **Updated:** 2026-05-05

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/x9281a7b4d)
- **Repository:** <https://github.com/behrensd/mcpwall>

## 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": "behrensd-mcpwall"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/behrensd-mcpwall` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/behrensd-mcpwall/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