Skip to content
MCP server

TradeCanvas

Look up and validate TradeCanvas chart indicators, options and drawing tools

Runs locallyStatus and history
Install
Pricing
Open source
Platforms
CLI, Windows, macOS
Runs
Locally
Version
1.61.0
Listing updated
3 days ago

About TradeCanvas

TradeCanvas is an open-source MCP server for developer tools. It runs locally on your machine and is started by your AI client.

Coding agents often guess option names for a charting library and get them wrong. This server answers from a catalog generated out of the TradeCanvas library's own code, so names, types and allowed values match the installed version. All tools are read-only and the README says none touches the network or your files.

The most distinctive tool is validate_options. Give it a target such as ChartWidget and an options object, and it flags unknown names with the likely intended one, values outside the allowed set, numbers passed as strings, bad intervals and feature switches, and warns when a language such as Japanese needs its locale registered first. Other tools list indicators with their default params and line keys, drawing tools and the points they need, finance charts like depth and equity curves, widget features and style keys.

It runs over stdio through npx and needs Node 20.19 or later. The library itself is MIT licensed, and an optional agent skill teaches the wider API.

Install

Run in a terminal

claude mcp add tradecanvas -- npx -y @tradecanvas/mcp

Add to claude_desktop_config.json

{
  "mcpServers": {
    "tradecanvas": {
      "command": "npx",
      "args": [
        "-y",
        "@tradecanvas/mcp"
      ]
    }
  }
}
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

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

Add to .vscode/mcp.json

{
  "servers": {
    "tradecanvas": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@tradecanvas/mcp"
      ]
    }
  }
}

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

{
  "mcpServers": {
    "tradecanvas": {
      "command": "npx",
      "args": [
        "-y",
        "@tradecanvas/mcp"
      ]
    }
  }
}

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

{
  "mcpServers": {
    "tradecanvas": {
      "command": "npx",
      "args": [
        "-y",
        "@tradecanvas/mcp"
      ]
    }
  }
}

Tools this server provides (8)

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

list_indicators
Built-in indicators with id, name and whether they draw over price or in a pane
get_indicator
One indicator in full: params, inputs, line keys, levels and sample code
list_drawing_tools
Drawing tools, their type values, points and options
list_finance_charts
Non-trading charts such as bars, donut, depth, equity curve, market map and gauge
list_options
Options of ChartWidget, Chart, ChartWidgetGrid or a finance chart
list_widget_features
Names accepted by ChartWidget's features switch
list_style_keys
Style keys and values for overrides
validate_options
Check an options object before use

What it does

Indicator catalog
List indicators and read one in full, including default params, line keys and sample code.
Drawing tool lookup
Find the type value and required points for each drawing tool.
Options validation
Catch unknown option names, bad values and mistyped numbers before use.
Finance chart list
See non-trading charts such as bars, donut, depth and gauge by class name.
Style and feature keys
List widget feature switches and the style keys accepted by overrides.
Version-matched answers
The catalog is generated from the library's code, so it follows the same release.

Good for

  • Stop an agent inventing option names for ChartWidget
  • Check an options object before running it
  • Find the right key for an indicator's output line
  • Pick a drawing tool and see how many points it needs
  • Add the server to Claude Code, Cursor or Codex with one command

Pricing

Open source

MIT licensed

Prices change. Check tradecanvas.dev before you buy.

TradeCanvas FAQ

What does it need to run?

Node 20.19 or later; it starts over stdio with npx -y @tradecanvas/mcp.

Does it access my files or the network?

The README says all tools are read-only and none touches the network or your files.

What licence applies?

The README states MIT.

Does it work on Windows?

Yes, with a cmd /c wrapper around npx outside WSL, as the README shows.

Is TradeCanvas free?

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

How do I add TradeCanvas to Claude Code?

Run this command in your terminal: claude mcp add tradecanvas -- npx -y @tradecanvas/mcp

What are the best alternatives to TradeCanvas?

The closest alternatives to TradeCanvas are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to TradeCanvas

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools