mcpField
C
chart-context

chart-context

Local
mylinedchart.comFinance1Updated 18w ago
RepositoryVisit website

About chart-context

chart-context is a read-only MCP server for AI agents that need live chart and workspace details from the MyLinedChart desktop app. It runs locally and redacts account identifiers and credentials from returned context.

Key features

  1. 01Read current chart and workspace summary
  2. 02Retrieve recent OHLCV candles
  3. 03Inspect chart drawings and price levels
  4. 04View configured indicator settings
  5. 05Check IBKR and market-data provider status

Use cases

  1. 01Provide an agent with current chart context
  2. 02Review recent candle data through an agent
  3. 03Check connection and feed status without exposing credentials

MCP support

The MCP server exposes five read-only tools for chart context, candles, drawings, indicators, and provider status. It requires the MyLinedChart desktop app and runs on the same machine.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "com-mylinedchart-chart-context": {
      "command": "npx",
      "args": [
        "-y",
        "@mylinedchart/mcp-chart-context"
      ],
      "env": {
        "MLC_CONTEXT_FILE": "<MLC_CONTEXT_FILE>"
      }
    }
  }
}
Run commandnpx -y @mylinedchart/mcp-chart-context
Environment variables to set
MLC_CONTEXT_FILEOptional override path to the MyLinedChart agent-context.json file. The server auto-detects the default location; set this only if your app data is in a non-standard location.

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@mylinedchart/mcp-chart-context0.1.1

Tools

5

Saved tool list · updated 2w ago

This tool takes no parameters.

Details

From the project README

@mylinedchart/mcp-chart-context

Read-only MCP server giving AI agents read-only access to your live MyLinedChart desktop chart and workspace context. Requires the MyLinedChart desktop app. Full docs: mylinedchart.com/mcp

Tools

ToolPurpose
get_chart_contextReturns the current MyLinedChart chart and workspace summary: symbol, timeframe, range, provider, connection state, feed type, candle/drawing/indicator counts, diagnostics ID, and data freshness. Read-only.
get_candlesReturns the most-recent OHLCV candle bars for the current chart. Fields: timestamp (epoch ms), open, high, low, close, volume. Read-only.
get_drawingsReturns all drawings and price levels for the current chart symbol: trend lines, horizontal levels, note labels, and other overlays. Read-only.
get_indicatorsReturns the configured indicators for the current chart: name, calculation parameters, placement (main/lower), and visibility. Does NOT include series data. Read-only.
get_provider_statusReturns IBKR connector and market-data provider status: connection state, MarketDataStatus code, feed type (delayed/live), diagnostics ID, and last-updated. Never exposes account IDs, credentials, or bridge URLs. Read-only.

Privacy & safety

  • Read-only. No mutations, no order entry, no trading.
  • Local. The server runs on your machine alongside the desktop app. Nothing leaves your machine.
  • Redacted. Account IDs, credentials, bridge URLs, and session tokens are stripped before any context is returned.

Install

npm install -g @mylinedchart/mcp-chart-context

Node 18 or later required.

Usage

Add to your AI agent's MCP config (claude_desktop_config.json or ~/.claude/settings.json):

{
  "mcpServers": {
    "mylinedchart": {
      "command": "mlc-mcp"
    }
  }
}

Then:

  1. Download and open the MyLinedChart desktop app (mylinedchart.com/resources/downloads).
  2. Enable the MCP server in-app (Settings → MCP).
  3. Load a chart. Your AI agent can now call the five read-only tools above.
Override the context file path
MLC_CONTEXT_FILE=/custom/path/agent-context.json mlc-mcp

Links

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.