# customhouse

> customhouse — vineetpant-customhouse. Use this tool when you need to secure agent sessions from potential security threats by blocking malicious tool calls. It solves problems related to data egress and unauthorized money transfers by proxying MCP requests and filtering out untrusted content. The customhouse tool takes in agent sessions and MCP requests as input and outputs a secured session with blocked malicious calls.

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

## Description

Deterministic MCP proxy that blocks money-moving and data-egress tool calls in any agent session that has received untrusted content. No model in the decision path.

## Trust

- **Trust score (0–1):** 0.56
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** Apache-2.0
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/vineetpant/customhouse)

## 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": "vineetpant-customhouse"
    }
  }
}
```

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