# Capsule server

> Use this tool when you need to execute untrusted code in a secure environment, solving problems related to code isolation and security risks. The capsule-mcp-server takes in Python and JavaScript code as input and outputs the execution results, providing a safe interface for running potentially malicious code. It is ideal for use cases where code from untrusted sources needs to be executed, such as in AI model testing or code validation scenarios.

Canonical page: https://skillsregistry.net/skills/mavdol-capsule-mcp-server  
JSON: https://api.skillsregistry.net/v1/skills/mavdol-capsule-mcp-server

## Description

Capsule MCP server gives your AI agent the ability to safely run untrusted Python and JavaScript code in a secure WebAssembly sandbox.

## 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:** ai-ml
- **Updated:** 2026-05-12

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/j7bwggauln)
- **Repository:** <https://github.com/capsulerun/capsule>

## 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": "mavdol-capsule-mcp-server"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/mavdol-capsule-mcp-server` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/mavdol-capsule-mcp-server/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