# Kody

Kody gives AI agents cloud storage for memory, keys, code, and automations. Use it when an agent needs search and execution through MCP.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed · ★ 851
- Author: kody-hq
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/kody-hq/kody
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/mcp/kody

## What it does

Kody connects an agent to cloud-hosted state for memory, keys, code, and automations. Its MCP surface centers on search and code execution instead of a large fixed tool list. The same server can be used from compatible MCP hosts.

The service supports individuals and teams, with isolated packages, jobs, credentials, memories, and related state for each account. Its architecture uses Cloudflare Workers, OAuth-protected MCP endpoints, and separate workers for package runtime and jobs.

Claude Code connects to Kody over HTTP at `https://kody.codes/mcp`; a compatible MCP host is required for this setup to work. The server can also be configured in Codex, Cursor, GitHub Copilot, Cline, Zed, and Windsurf (Devin Desktop).

## Requirements
- Remote server: `https://kody.codes/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http kody https://kody.codes/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add kody --url https://kody.codes/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "kody": {
            "url": "https://kody.codes/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "kody": {
            "type": "http",
            "url": "https://kody.codes/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http kody https://kody.codes/mcp
```

## When to use it
- store agent memory across tasks
- search data through MCP
- run operations through Code Mode
- separate team packages and credentials

## Example prompts
- Search the agent memory for this project's setup details.
- Use Kody to check which packages are available for the current task.
- Save this key and use it when the next job runs.

## Similar
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33918
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81115
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119160
- [Codebase Memory](https://affpapa.org/en/nevibecode/mcp/codebase-memory.md) — MCP server · ★ 47392
- [mcp-server](https://affpapa.org/en/nevibecode/mcp/mcp-server.md) — MCP server · ★ 43872
- [AIHawk](https://affpapa.org/en/nevibecode/mcp/aihawk.md) — MCP server · ★ 32221

---
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