# mcpfence

> mcpfence — zyk200536-eng-mcpfence. Use this tool when you need to control and secure interactions between your agent client and MCP servers. The mcpfence tool observes, tightens, and intercepts permissions, solving problems related to unauthorized access and data breaches. It takes in agent client requests and MCP server responses as inputs, producing filtered and secured outputs to ensure a safe and reliable connection.

Canonical page: https://skillsregistry.net/skills/zyk200536-eng-mcpfence  
JSON: https://api.skillsregistry.net/v1/skills/zyk200536-eng-mcpfence

## Description

Local-first MCP permission firewall: observe, tighten, intercept. Sits between your agent client and MCP servers.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-11-05

## Source

- **Source listing:** [GitHub](https://github.com/zyk200536-eng/mcpfence)

## 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": "zyk200536-eng-mcpfence"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/zyk200536-eng-mcpfence` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/zyk200536-eng-mcpfence/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