# codex-mcp-swarm

> Use this tool when you need to execute multiple tasks in parallel with conflict-free isolation and real-time monitoring. It solves problems of slow task execution, resource conflicts, and limited visibility into task progress by wrapping OpenAI's Codex CLI with parallel execution and live monitoring capabilities. It takes in tasks and Codex configurations as inputs and outputs real-time task status and results.

Canonical page: https://skillsregistry.net/skills/tkasperczyk-codex-mcp-swarm  
JSON: https://api.skillsregistry.net/v1/skills/tkasperczyk-codex-mcp-swarm

## Description

Wraps OpenAI's Codex CLI with true parallel task execution, worktree isolation for conflict-free runs, and live monitoring of each task.

## Trust

- **Trust score (0–1):** 0.64
- **Verification tier:** scanned
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-03

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/wzxre65hl8)
- **Repository:** <https://github.com/TKasperczyk/codex-mcp-swarm>

## 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": "tkasperczyk-codex-mcp-swarm"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/tkasperczyk-codex-mcp-swarm` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/tkasperczyk-codex-mcp-swarm/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