# Agentmailbox Claude Code

> >

- **Type:** Skill
- **Install:** `agentstack add skill-ragavrida-agentsmcp-claude-code`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [RagavRida](https://agentstack.voostack.com/s/ragavrida)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [RagavRida](https://github.com/RagavRida)
- **Source:** https://github.com/RagavRida/agentsmcp/tree/main/skills/claude-code

## Install

```sh
agentstack add skill-ragavrida-agentsmcp-claude-code
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# AgentMailbox — Context Sync for Claude Code

**Your context follows you across terminal sessions and tools.**

AgentMailbox gives Claude Code persistent memory across sessions. Combined
with `CLAUDE.md` for static project context, AgentMailbox provides dynamic,
evolving context that tracks decisions, progress, and open questions across
every session and every tool.

## Setup

### 1. Add MCP to Claude Code

Add to your Claude Code MCP settings:

```json
{
  "mcpServers": {
    "agentsmcp": {
      "command": "npx",
      "args": ["-y", "agentsmcp-adapter"],
      "env": {
        "AGENTSMCP_AGENT_ID": "claude-code@local",
        "AGENTSMCP_SERVER": "http://localhost:3000"
      }
    }
  }
}
```

### 2. Start the Server

```bash
npx agentsmcp-server
# Runs at http://localhost:3000
```

Or use the demo server:
```
AGENTSMCP_SERVER=https://hdnxa5c8yr.us-east-1.awsapprunner.com
```

## How It Works with CLAUDE.md

| Layer | Purpose | Persistence |
|:------|:--------|:------------|
| **CLAUDE.md** | Static project context (coding standards, architecture, conventions) | File-based, manual |
| **AgentMailbox** | Dynamic session context (decisions, progress, open questions, handoffs) | Server-backed, automatic |

Use both together:
- `CLAUDE.md` for _what the project is_
- AgentMailbox for _what happened and what's next_

## Workflows

### Session Start

```
Tool: agentsmcp_receive
```

Check for context from previous sessions or messages from other agents/tools.

### After Terminal Work

Record what you accomplished:

```
Tool: agentsmcp_send
Arguments:
  to: "claude-code@local"
  body: {
    "session": "Terminal session summary",
    "commands": ["npm test — all passing", "npm run build — clean"],
    "decisions": ["Migrated to ESM modules"],
    "filesChanged": ["package.json", "tsconfig.json", "src/index.ts"],
    "remainingTasks": ["Update CI config for ESM"]
  }
```

### Handoff to GUI Tools

When the user wants to continue in Cursor or Claude Desktop:

```
Tool: agentsmcp_send
Arguments:
  to: "cursor@local"
  body: {
    "handoff": "ESM migration 80% complete",
    "remainingWork": "Update CI pipeline, fix 2 failing integration tests",
    "context": "See thread for full migration log"
  }
```

## Tool Reference

| Tool | Purpose |
|:-----|:--------|
| `agentsmcp_receive` | Get unread messages with full context |
| `agentsmcp_send` | Send a message / record progress |
| `agentsmcp_sync` | Rejoin a thread with full context |
| `agentsmcp_threads` | List all threads |
| `agentsmcp_mark_read` | Mark a thread as read |
| `agentsmcp_reply_all` | Reply to all participants |

## Links

- **GitHub**: https://github.com/RagavRida/agentsmcp
- **npm**: https://www.npmjs.com/package/agentsmcp

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [RagavRida](https://github.com/RagavRida)
- **Source:** [RagavRida/agentsmcp](https://github.com/RagavRida/agentsmcp)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-ragavrida-agentsmcp-claude-code
- Seller: https://agentstack.voostack.com/s/ragavrida
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.