# TradeMemory Protocol MCP server

> Record trading decisions in a tamper-evident audit trail and recall past losses before an AI agent places the next order.

- Listing: https://mcp.tc/i/tradememory-protocol
- Connect: this is a local (stdio) server; install it on your machine (see Install). The listing link is a page, not an MCP endpoint.
- Type: local (stdio)
- Auth: no API key needed
- Category: [Finance & Payments](https://mcp.tc/c/finance-payments)
- Vendor: mnemox-ai
- Homepage: <https://mnemox.ai/tradememory/>
- Docs: <https://github.com/mnemox-ai/tradememory-protocol/tree/master/docs>
- Repository: <https://github.com/mnemox-ai/tradememory-protocol>
- Package: pypi `tradememory-protocol`

## About

TradeMemory is a local-first memory and audit layer for AI trading agents. It stores trades and decisions, ranks recalled memories by outcome (with a losses-first option), and chains records with SHA-256 hashes and RFC 3161 anchoring. It can sync fills from Hyperliquid, Alpaca, MT5 and Binance and report where your own history loses money. An optional proxy sits between the agent and an Alpaca MCP server and refuses orders that break a policy you set.

It runs locally over stdio, started with uvx tradememory-protocol (Python package on PyPI), or from source or Docker. No hosted endpoint or account is needed. Broker syncs use your own keys from your environment, and the optional evolution and replay features use Anthropic or DeepSeek keys only if you set them.

## What it can do

- Record trades and decisions with reasoning via remember\_trade
- Recall past trades weighted by outcome, with losses-first ordering
- Keep a tamper-evident SHA-256 hash-chained audit log
- Sync fills from Hyperliquid, Alpaca, MT5 and Binance
- Report where your own trade history loses money
- Pre-check orders with evaluate\_order against your policy
- Proxy an Alpaca MCP server and refuse orders that break your rules

## Example prompts

- "Record my AAPL long at $195, earnings beat, high confidence."
- "Recall my past losing trades on XAUUSD before I propose a new order."
- "Sync my Hyperliquid fills and show where my history loses money."
- "Check whether this order breaks my position and notional limits."

## Install

### Claude Code

1. Run this in a terminal, in your project folder:

```bash
claude mcp add --transport stdio tradememory-protocol -- uvx tradememory-protocol
```

2. Start Claude Code and type `/mcp`. **tradememory-protocol** should show as connected.

Add `--scope user` to make it available in every project.

### Claude Desktop

1. Open **Settings → Developer → Edit Config**. It opens `claude_desktop_config.json`. Add:

`claude_desktop_config.json`:

```json
{
  "mcpServers": {
    "tradememory-protocol": {
      "command": "uvx",
      "args": [
        "tradememory-protocol"
      ]
    }
  }
}
```

2. Save the file and restart Claude Desktop.

Needs uv (Python) on your computer. The file lives in `~/Library/Application Support/Claude/` on macOS and `%APPDATA%\Claude\` on Windows.

### Cursor

[Add to Cursor](<https://cursor.com/install-mcp?name=tradememory-protocol&config=eyJjb21tYW5kIjoidXZ4IiwiYXJncyI6WyJ0cmFkZW1lbW9yeS1wcm90b2NvbCJdfQ%3D%3D>) (opens Cursor)

Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project):

`mcp.json`:

```json
{
  "mcpServers": {
    "tradememory-protocol": {
      "command": "uvx",
      "args": [
        "tradememory-protocol"
      ]
    }
  }
}
```

Needs uv (Python) on your computer.

### VS Code

[Install in VS Code](<https://vscode.dev/redirect/mcp/install?name=tradememory-protocol&config=%7B%22type%22%3A%22stdio%22%2C%22command%22%3A%22uvx%22%2C%22args%22%3A%5B%22tradememory-protocol%22%5D%7D>) (opens VS Code)

Or from a terminal:

```bash
code --add-mcp '{"name":"tradememory-protocol","type":"stdio","command":"uvx","args":["tradememory-protocol"]}'
```

Or commit it to the repo in `.vscode/mcp.json`:

`.vscode/mcp.json`:

```json
{
  "servers": {
    "tradememory-protocol": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "tradememory-protocol"
      ]
    }
  }
}
```

Needs uv (Python) on your computer.

### Devin Desktop

1. Add it to `~/.config/devin/mcp_config.json` (macOS and Linux) or `%APPDATA%\devin\mcp_config.json` (Windows):

`mcp_config.json`:

```json
{
  "mcpServers": {
    "tradememory-protocol": {
      "command": "uvx",
      "args": [
        "tradememory-protocol"
      ]
    }
  }
}
```

2. Refresh the MCP server list in Cascade.

Devin Desktop is the new name for Windsurf.

### Codex

```bash
codex mcp add tradememory-protocol -- uvx tradememory-protocol
```

Or edit `~/.codex/config.toml` directly:

`config.toml`:

```toml
[mcp_servers.tradememory-protocol]
command = "uvx"
args = ["tradememory-protocol"]
```

Needs uv (Python) on your computer.

### Gemini CLI

```bash
gemini mcp add tradememory-protocol uvx tradememory-protocol
```

This adds it to the current project. Add `-s user` to use it everywhere.

### Any client

Most clients that start local servers accept this shape:

```json
{
  "mcpServers": {
    "tradememory-protocol": {
      "command": "uvx",
      "args": [
        "tradememory-protocol"
      ]
    }
  }
}
```

Zed puts servers under `context_servers` in its settings, with the same `command`, `args` and `env` fields.

Needs uv (Python) on your computer.

## Recent changes

- 2026-10-08 04:20 UTC: Tracking started: version 0.5.6. Source: automatic check.

More on the History tab, with descriptions before and after for the newest entries: https://mcp.tc/i/tradememory-protocol#history (Atom feed: https://mcp.tc/i/tradememory-protocol/history.xml). It records what mcp.tc's anonymous checks saw, every 3 hours where the tool list can be read without sign-in; it is not a security review.

## Details

- Server version: 0.5.6
- Last checked: 2026-10-08
- Listed: 2026-10-08
- Updated: 2026-10-08

---
Source: https://mcp.tc/i/tradememory-protocol (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report
