Skip to content
MCP server

Deptho

Replay crypto backtest orders against real trades and write tearsheets locally

Runs locallyStatus and history
Install
Pricing
Open source
Platforms
CLI, self-hosted
Runs
Locally
Version
0.1.0
Listing updated
3 days ago

About Deptho

Deptho is an open-source MCP server for finance and payments. It runs locally on your machine and is started by your AI client.

Deptho's server targets a specific question in crypto backtesting: how much of a strategy's return survives realistic execution. It takes an orders file and a trades file, models each order as filling at the volume-weighted price of same-side trades that followed it until its size is covered, and reports slippage as mean, median, 90th and 99th percentile in basis points. Order book depth and queue position are not modelled, and the README says so.

A second tool turns a bars file with time, price and position into a self-contained HTML tearsheet that splits returns into fees, funding and slippage. Trades can come from Binance archive aggTrades files or Tardis.dev trades files.

It runs over stdio on your machine from a pip package, works on local files and sends nothing to Deptho. Pro tools for syncing Binance USD-M archive days and replaying against that dataset need a separate Deptho Pro licence; the code is Apache-2.0.

Install

Run in a terminal

claude mcp add deptho-mcp -- uvx deptho-mcp

Add to claude_desktop_config.json

{
  "mcpServers": {
    "deptho-mcp": {
      "command": "uvx",
      "args": [
        "deptho-mcp"
      ]
    }
  }
}
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "deptho-mcp": {
      "command": "uvx",
      "args": [
        "deptho-mcp"
      ]
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "deptho-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "deptho-mcp"
      ]
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "deptho-mcp": {
      "command": "uvx",
      "args": [
        "deptho-mcp"
      ]
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "deptho-mcp": {
      "command": "uvx",
      "args": [
        "deptho-mcp"
      ]
    }
  }
}

Tools this server provides (5)

Taken from the project documentation; the running server may differ.

replay_orders
Replays an orders CSV against a trades file and returns fills plus a slippage summary.
tearsheet
Builds an HTML report from a bars CSV and returns its path and headline numbers.
pro_status
Reports whether Deptho Pro is installed and licensed.
pro_sync
Pro: downloads Binance USD-M days into a local dataset.
pro_replay
Pro: replays an orders CSV against that dataset.

What it does

Order replay
Fills each order from later same-side trade prints and summarises slippage.
Tearsheets
Generates an HTML report splitting returns into fees, funding and slippage.
Local only
Reads and writes local files and sends nothing to Deptho.
Common trade formats
Accepts Binance aggTrades and Tardis.dev trades files.
Pro dataset tools
Optional tools download Binance USD-M days and replay against them.

Good for

  • Estimate real slippage for a strategy's market orders
  • Produce a shareable performance report after a backtest
  • Separate fees and funding from slippage in returns
  • Let a coding assistant run execution checks on local data

Pricing

Open source

Apache-2.0; some tools need a Deptho Pro licence

Prices change. Check deptho.io before you buy.

Deptho FAQ

Does any data leave my machine?

No. Every tool works on local files; the only download is Pro's sync from Binance's public archive when you ask.

How are fills modelled?

At the VWAP of same-side trades after the order until its size is covered; order book depth and queue position are not modelled.

What input formats are needed?

An orders CSV with time, side and qty, plus a Binance aggTrades or Tardis.dev trades file.

How do I install it?

pip install deptho-mcp, then add it with claude mcp add deptho -- deptho-mcp or the equivalent config in Claude Desktop or Cursor.

Is Deptho free?

Yes. Deptho is open source, so you can use and self-host it for free.

How do I add Deptho to Claude Code?

Run this command in your terminal: claude mcp add deptho-mcp -- uvx deptho-mcp

What are the best alternatives to Deptho?

The closest alternatives to Deptho are Agent-Native Analytics, Google Ads + Meta Ads + SEO/GEO MCP, Solana MCP by Vybe, Tapetide - Indian Stock Market MCP and World Monitor.

Alternatives to Deptho

  1. Open-source analytics app where an AI agent builds charts and dashboards from your data

    • Remote
    • Open source
    • 7.7K GitHub stars
    • Analytics and data
  2. Hosted MCP connector for managing Google Ads, Meta Ads, GA4 and Search Console from chat

    • 8 tools
    • Remote
    • Freemium
    • 8.1K GitHub stars
    • Marketing and SEO
  3. Remote MCP server exposing the Vybe Solana API to AI clients and code editors

    • 44 tools
    • Remote
    • 2.8K GitHub stars
    • Finance and payments
  4. Indian NSE and BSE stock market data for AI assistants through 48 MCP tools

    • 17 tools
    • Remote
    • Freemium
    • 150 GitHub stars
    • Finance and payments
  5. World Monitor

    MCP server

    Live geopolitical intelligence dashboard with an API and MCP server for agents

    • Remote
    • Freemium
    • Analytics and data
  6. Budget Tracker

    MCP server

    Local MCP expense ledger that logs receipts and mileage, splits VAT and prepares rebilling

    • 14 tools
    • Remote
    • Freemium
    • 2 GitHub stars
    • Finance and payments