# AgentWall

> Use this tool when you need to enforce security policies and protect sensitive resources from malicious tool calls. AgentWall acts as a proxy, blocking dangerous calls before execution to safeguard credentials, filesystem, shell, and databases across various platforms. Ideal for use cases requiring robust security measures to prevent unauthorized access and potential data breaches.

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

## Description

Policy-enforcing MCP proxy that blocks dangerous tool calls before they execute. Protects credentials, filesystem, shell, and databases across Claude Desktop, Cursor, Windsurf, and OpenClaw.

## Trust

- **Trust score (0–1):** 0.74
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

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

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/sgqqtsxge0)
- **Repository:** <https://github.com/agentwall/agentwall>

## 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": "agentwall-agentwall"
    }
  }
}
```

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