# Harny Action Record

The Harny Action Record MCP server for Claude Code keeps a history of agent actions. Each entry records what happened, who it was for, when it occurred, and its result.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI
- Author: harny-ai
- License: Apache-2.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/harny-ai/skills
- Updated: 2026-11-13
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/harny-action-record

## What it does

Harny Action Record keeps an audit history of an agent's actions, including the action, its recipient, the time, and the outcome. Ask the agent to retrieve entries from that history.

The server connects over HTTP at `https://mcp.harny.ai/record`. The Harny setup also calls for one API key and a model of your own.

## Requirements
- Remote server: `https://mcp.harny.ai/record`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http action-record https://mcp.harny.ai/record
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add harny-action-record --url https://mcp.harny.ai/record
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "harny-action-record": {
            "url": "https://mcp.harny.ai/record"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "harny-action-record": {
            "type": "http",
            "url": "https://mcp.harny.ai/record"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http harny-action-record https://mcp.harny.ai/record
```

## When to use it
- keep a history of agent actions
- find out who an action was performed for
- check when an action happened and how it ended

## Example prompts
- Show me the agent's action history.
- What did the agent do for this user, and what was the outcome?
- When did the agent last take an action?

## Similar
- [architecture-decision-record](https://affpapa.org/en/nevibecode/skills/architecture-decision-record.md) — skill · 1500 installs
- [safe-action-middleware](https://affpapa.org/en/nevibecode/skills/safe-action-middleware.md) — skill · 1200 installs
- [browser-record](https://affpapa.org/en/nevibecode/skills/browser-record.md) — skill · 719 installs
- [admin-dashboard](https://affpapa.org/en/nevibecode/skills/admin-dashboard.md) — skill · 338 installs
- [record-a-decision](https://affpapa.org/en/nevibecode/skills/record-a-decision.md) — skill · 252 installs
- [Filelayer](https://affpapa.org/en/nevibecode/mcp/filelayer.md) — MCP server

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
