Skip to main content
Glama
cowpin-ai

Cowpin Agent Memory MCP Server

Official
by cowpin-ai
README.md
# Cowpin Agent Memory MCP Server

[![Smithery](https://smithery.ai/badge/@cowpin/mcp-server)](https://smithery.ai/server/@cowpin/mcp-server)
[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](https://opensource.org/licenses/MIT)

Official [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) server for **[Cowpin](https://www.cowpin.com)** — the world's first **Dual-Species Memory Vault** for humans and autonomous AI agents.

Gives **Claude Desktop**, **Cursor IDE**, **Windsurf**, and autonomous agents persistent long-term memory, zero-JS web page extraction, full-text S3 archiving, and 1536-dimensional semantic vector recall (`pgvector`).

---

## ⚡ Quick Start

### 1. Claude Desktop Setup
Add this to your `claude_desktop_config.json`:

- **macOS**: `~/Library/Application Support/Claude/claude_desktop_config.json`
- **Windows**: `%APPDATA%\Claude\claude_desktop_config.json`

```json
{
  "mcpServers": {
    "cowpin": {
      "command": "npx",
      "args": ["-y", "@cowpin/mcp-server"],
      "env": {
        "COWPIN_AGENT_API_KEY": "cw_agent_your_api_key_here",
        "COWPIN_API_URL": "https://www.cowpin.com"
      }
    }
  }
}
```

### 2. Cursor IDE Setup
In Cursor settings or `.cursor/mcp.json`:

```json
{
  "mcpServers": {
    "cowpin": {
      "command": "npx",
      "args": ["-y", "@cowpin/mcp-server"],
      "env": {
        "COWPIN_AGENT_API_KEY": "cw_agent_your_api_key_here"
      }
    }
  }
}
```

### 3. Smithery One-Click Install
Install automatically via Smithery CLI:

```bash
npx -y @smithery/cli install @cowpin/mcp-server --client claude
```

---

## 🛠 Available Tools

| Tool | Description |
| :--- | :--- |
| `cowpin_save_memory` | Fetches any URL, cleans DOM bloat, extracts readable text, generates vector embeddings, and permanently archives it in Cowpin. Also accepts raw markdown notes. |
| `cowpin_search_memory` | Performs hybrid Reciprocal Rank Fusion search across past research, articles, and notes using full-text keyword matching and pgvector semantic similarity. |
| `cowpin_get_balance` | Checks on-chain micro-credit balance and treasury deposit addresses (Base USDC, Solana, etc.). |
| `cowpin_get_memory_page` | Retrieves the full archived text and snapshot of a previously saved memory by ID or URL. |

---

## 🔑 Authentication

1. **Humans**: Generate an Agent API Key directly in your Cowpin account dashboard at [cowpin.com/settings/tokens](https://www.cowpin.com/settings/tokens).
2. **Autonomous Agents**: Sign an on-chain challenge using your Base, EVM, or Solana wallet address to receive an instant API token and micro-credit balance. See [cowpin.com/docs/agent](https://www.cowpin.com/docs/agent).

---

## 📄 License
MIT License. Created by [Cowpin](https://www.cowpin.com).

TDQS

A3.9/5.0

Scored across 4 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: saving, searching, checking balance, and retrieving full memory pages. Even though search returns snippets and get_memory_page returns full text, they serve different functions and are unlikely to be confused.

Naming Consistency5/5

All tools follow the consistent pattern cowpin_<verb>_<object> (save_memory, search_memory, get_balance, get_memory_page). The 'get' prefix is used consistently for retrieval operations, making the naming predictable and uniform.

Tool Count5/5

With 4 tools, the server is well-scoped for its purpose as a memory vault. The count is neither too thin nor excessive, and each tool contributes to core workflows (save, search, retrieve, and billing awareness).

Completeness4/5

The server covers save, search, and full-text retrieval, which are the primary operations for a memory vault. However, it lacks update and delete capabilities, which could be relevant if users need to correct or remove stored memories, though this may be intentional.

Maintenance

ActivityMaintained
ResponsivenessNo issues