Trading212 Mcp Server

io.github.KyuRishPublished by GitHub account KyuRishv0.1.1Updated Oct 24, 2026

MCP server for Trading 212 API - portfolio, orders, pies, dividends, and analytics

VerifiedSTDIODesktop onlyFinanceData & Analytics

Overview

AI-generated overview

Connects an AI assistant to a Trading 212 brokerage account to review portfolios, place orders, manage pies and analyze dividends.

What you can do
  • Read account data: account info, cash balance, open positions and single-position lookups
  • Place and manage orders: market, limit, stop and stop-limit orders, list and cancel pending orders
  • Manage investment pies: list, inspect, create, update, duplicate and delete pies
  • Look up market data: search tradeable instruments and exchanges
  • Review history: past orders, paid dividends, transactions and CSV export requests
  • Run composite analytics: portfolio summary, per-position performance, dividend summary and recent activity
When to use it
Useful when you want to ask questions about a Trading 212 portfolio in natural language, check balances and performance, review dividend income, or place and manage orders and pies without opening the app.
Requirements
Runs locally as a Python package (PyPI, launched with uvx or pip). Needs a Trading 212 API key and secret from Settings > API (Beta), supplied as TRADING212_API_KEY and TRADING212_API_SECRET, plus ENVIRONMENT set to live or demo. Network access to the Trading 212 API is required.
Before you install
The server holds brokerage API credentials that can place and cancel real orders and delete pies; set ENVIRONMENT to demo for paper trading until confident. Order placement and pie changes act on the account, and the assistant's requests are sent to Trading 212. Keep the API key and secret out of shared configuration files.

Installation

In SourceWeft

  1. Open Trading212 Mcp Server in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Trading 212 MCP Server

[PyPI] [Downloads] [License: MIT] [Glama] [Python] [MCP] [Tools]

Connect your AI assistant to your Trading 212 brokerage account. Ask questions about your portfolio, place trades, manage pies, and analyze dividends - all through natural language.

Works with Claude Desktop, Claude Code, ChatGPT, Gemini, Cursor, Windsurf, and any client that supports the Model Context Protocol (MCP).

Why this server?

  • 32 tools covering the full Trading 212 API, plus 4 analytics tools that combine multiple API calls into actionable insights
  • Smart rate limiting - reads T212's rate limit headers, auto-waits, and retries on 429 (up to 3 times). No rate limit errors leak to your AI
  • Zero config - install from PyPI, add your API key, done. No Docker, no database, no Redis
  • Typed responses - every tool returns structured Pydantic models, not raw JSON
  • Paper trading - set ENVIRONMENT=demo to test with virtual money first

What can it do?

CategoryToolsExamples
AnalyticsPortfolio summary, performance, dividends, activity"Show me my portfolio P&L"
TradingMarket, limit, stop, stop-limit orders"Buy 5 shares of AAPL"
PortfolioPositions, cash balance, account info"What's my cash balance?"
PiesCreate, update, duplicate, delete pies"Show my pie allocations"
Market DataInstrument search, exchange schedules"Search for Tesla"
HistoryPast orders, dividends, transactions, CSV exports"Show my dividend history"

Analytics tools

These combine multiple API calls into single high-level responses:

  • fetch_portfolio_summary - Complete snapshot: total value, P&L, cash, top holdings, allocation
  • fetch_portfolio_performance - Per-position returns with dividends, best/worst performers
  • fetch_dividend_summary - Income analysis grouped by ticker and month
  • fetch_recent_activity - Combined timeline of trades and transactions

Quick start

Install

bash
uvx trading212-mcp-server

Or via pip:

bash
pip install trading212-mcp-server

Get your API credentials

From the Trading 212 app: Settings > API (Beta). You need both the API Key and Secret - the server uses Basic Auth.

Connect to Claude Desktop

Add to claude_desktop_config.json (Windows: %APPDATA%\Claude\, Mac: ~/Library/Application Support/Claude/):

json
{  "mcpServers": {    "trading212": {      "command": "uvx",      "args": ["trading212-mcp-server"],      "env": {        "TRADING212_API_KEY": "<your-api-key>",        "TRADING212_API_SECRET": "<your-api-secret>",        "ENVIRONMENT": "live"      }    }  }}

Connect to Claude Code

bash
claude mcp add trading212 -- uvx trading212-mcp-server

Then set the environment variables in your shell or .env file.

Other clients (Cursor, Windsurf, ChatGPT, etc.)

Same command and env vars - configure per your client's MCP docs. Set ENVIRONMENT to demo for paper trading.

From source

bash
git clone https://github.com/KyuRish/trading212-mcp-server.gitcd trading212-mcp-servercp .env.example .env  # fill in your API keysuv syncuv run -m trading212_mcp_server.server
claude_desktop_config.json for source installs
json
{  "mcpServers": {    "trading212": {      "command": "uv",      "args": ["run", "--directory", "<path-to-repo>", "-m", "trading212_mcp_server.server"],      "env": {        "TRADING212_API_KEY": "<your-api-key>",        "TRADING212_API_SECRET": "<your-api-secret>",        "ENVIRONMENT": "live"      }    }  }}

All 32 tools

Analytics (composite)

ToolDescription
fetch_portfolio_summaryComplete portfolio snapshot with P&L and allocations
fetch_portfolio_performancePer-position returns, dividends, best/worst performers
fetch_dividend_summaryDividend income by ticker and month
fetch_recent_activityCombined timeline of trades and transactions

Account

ToolDescription
fetch_account_infoAccount metadata (currency, ID)
fetch_account_cashCash balance, invested value, P&L
fetch_all_open_positionsAll portfolio positions with live prices
search_specific_position_by_tickerSingle position lookup by ticker

Trading

ToolDescription
place_market_orderBuy/sell at current market price
place_limit_orderBuy/sell at specified price or better
place_stop_orderTrigger order at stop price
place_stop_limit_orderStop trigger with limit execution
fetch_all_ordersList all pending orders
fetch_orderGet specific order by ID
cancel_orderCancel a pending order

Pies

ToolDescription
fetch_piesList all investment pies
fetch_a_piePie details with instrument allocations
create_pieCreate a new pie with target weights
update_pieUpdate pie settings and allocations
duplicate_pieClone an existing pie
delete_pieRemove a pie

Market Data

ToolDescription
search_instrumentSearch tradeable instruments by ticker or name
search_exchangeSearch available exchanges

History

ToolDescription
fetch_historical_order_dataPast orders with pagination
fetch_paid_out_dividendsDividend payment history
fetch_transaction_listDeposits and withdrawals
fetch_exports_listList CSV export reports
request_csv_exportRequest a new CSV export

Compatibility

Tested with these MCP clients:

ClientStatus
Claude DesktopSupported
Claude CodeSupported
CursorSupported
WindsurfSupported
Any MCP-compatible clientSupported

Author

Built by Rishabh Dogra.

Support

If this server saves you time, a coffee would mean a lot.

[Buy Me a Coffee]

License

MIT

Source: README.md at commit 850da6b

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.1LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts