easy-equities-mcp
An MCP server that enables querying Easy Equities and Satrix investment accounts, including holdings, valuations, and transactions, via natural language.
README
easy-equities-mcp
An MCP server for Easy Equities and Satrix that lets any MCP-compatible client (e.g. Claude Desktop, Claude Code, Continue) query your investment accounts on demand.
Built on top of the unofficial
easy-equities-client
Python library.
[!WARNING] Unofficial. Not affiliated with Easy Equities or Satrix. Intended for personal use. You are responsible for your credentials and for respecting Easy Equities' terms of service.
Features
- Multiple accounts — configure any number of Easy Equities or Satrix logins side-by-side and reference them by name.
- No credentials in chat — usernames and passwords are loaded from
environment variables or a
.envfile, never passed through the MCP client. - Cookie persistence — successful logins are cached to disk so subsequent starts don't re-authenticate (and won't retrigger OTP).
- Refresh from chat — when cookies expire, the MCP client can refresh a session with a single tool call; no terminal required.
- CLI fallback — an
easy-equities-mcp-logincommand is included for seeding cookies before the MCP client is running.
Tools exposed
| Tool | Description |
|---|---|
list_sessions |
List active logged-in session names. |
refresh_session(session) |
Re-authenticate one session from config and save fresh cookies. |
refresh_all_sessions() |
Re-authenticate every configured session. |
list_accounts(session) |
List all accounts for a session (id, name, trading currency). |
get_holdings(session, account_id, include_shares=False) |
Holdings for an account. |
get_valuations(session, account_id) |
Valuation summary for an account. |
get_transactions(session, account_id) |
Transactions for the last year. |
get_transactions_for_period(session, account_id, start_date, end_date) |
Transactions between two YYYY-MM-DD dates. |
get_historical_prices(session, contract_code, period="OneYear") |
Historical prices. period is OneMonth, ThreeMonths, SixMonths, OneYear, or Max. |
Installation
Requires Python 3.13+. The recommended runner is
uv.
Option A — Run directly with uvx (zero install)
uvx easy-equities-mcp # run the MCP server
uvx easy-equities-mcp-login --list
Option B — pip install
pip install easy-equities-mcp
Option C — From source
git clone https://github.com/heinrich321/easyequities-mcp.git
cd easyequities-mcp
uv sync
uv run easy-equities-mcp
Configuration
Define your sessions
Each session is defined by three environment variables:
EE_SESSION_<NAME>_USERNAME=...
EE_SESSION_<NAME>_PASSWORD=...
EE_SESSION_<NAME>_PLATFORM=easyequities # or "satrix" — defaults to easyequities
<NAME> is any label you choose (letters, digits, underscores). It becomes
the lowercased session key you pass to the MCP tools. You can define as many
sessions as you want.
Example:
EE_SESSION_PERSONAL_USERNAME=you@example.com
EE_SESSION_PERSONAL_PASSWORD=hunter2
EE_SESSION_PERSONAL_PLATFORM=easyequities
EE_SESSION_TFSA_USERNAME=you@example.com
EE_SESSION_TFSA_PASSWORD=hunter2
EE_SESSION_TFSA_PLATFORM=satrix
You can reference personal and tfsa from chat after that.
Where to put the config
The server loads the first .env file it finds, in this order:
$EE_MCP_ENV_FILE(an explicit path)~/.config/easy-equities-mcp/.env— recommended for personal use./.envin the current working directory (handy for local dev)
Existing environment variables always win, so you can also skip the file and put everything in your MCP client's config block — see below.
Optional settings
| Variable | Default | Description |
|---|---|---|
EE_MCP_ENV_FILE |
unset | Explicit path to a .env file. |
EE_MCP_COOKIE_DIR |
~/.easy-equities-mcp |
Where session cookies are cached. |
Using it with Claude Desktop
-
Install the server (see above).
-
Put your session credentials in
~/.config/easy-equities-mcp/.env, or define them in theenvblock below. -
Edit your Claude Desktop config:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
Add the server. If you installed via
pip/uvx:{ "mcpServers": { "easy-equities": { "command": "uvx", "args": ["easy-equities-mcp"] } } }Or, equivalently with credentials in the config (skip the
.envfile):{ "mcpServers": { "easy-equities": { "command": "uvx", "args": ["easy-equities-mcp"], "env": { "EE_SESSION_PERSONAL_USERNAME": "you@example.com", "EE_SESSION_PERSONAL_PASSWORD": "hunter2", "EE_SESSION_PERSONAL_PLATFORM": "easyequities" } } } }Or, from a local checkout:
{ "mcpServers": { "easy-equities": { "command": "uv", "args": ["run", "--directory", "/absolute/path/to/easyequities-mcp", "easy-equities-mcp"] } } } - macOS:
-
Restart Claude Desktop.
Typical chat flow
You: Show me my current holdings.
Claude: [calls list_sessions → list_accounts("personal") → get_holdings("personal", "12345")]
When cookies eventually expire:
You: My personal session keeps failing.
Claude: [calls refresh_session("personal")]
No terminal required.
CLI
easy-equities-mcp-login is a small helper for when the MCP client isn't
running yet — for example, if you want to seed cookies after a fresh OTP
challenge.
easy-equities-mcp-login --list # list configured sessions
easy-equities-mcp-login personal # log in and save cookies
OTP / 2FA
The underlying library does a plain form POST and does not implement EE's OTP flow. In practice EE only challenges on a new device/IP and then sets a trust cookie, so the typical workaround is:
- Log in once via the EE website in a browser on the same machine (satisfies the OTP challenge and marks the device as trusted).
- Run
easy-equities-mcp-login <name>or call therefresh_sessionMCP tool — the Python client inherits the trusted-device status and saves its own cookies. - From then on, the MCP server reuses those cookies on every restart.
If EE still challenges the CLI login after trusting the device in a browser, please open an issue with the error message so OTP support can be added.
Security notes
- The server stores session cookies under
~/.easy-equities-mcp/with mode0700/0600. Anyone with access to that directory can impersonate the logged-in user. .envfiles should be kept at0600and never committed. The repo's.gitignoreexcludes them by default.- No credentials are ever sent through the MCP channel itself. Only metadata like session names.
Development
git clone https://github.com/heinrich321/easyequities-mcp.git
cd easyequities-mcp
uv sync
uv run pytest
The server uses stdio transport. You can poke at it directly with JSON-RPC:
printf '%s\n%s\n%s\n' \
'{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"test","version":"1.0"}}}' \
'{"jsonrpc":"2.0","method":"notifications/initialized","params":{}}' \
'{"jsonrpc":"2.0","id":2,"method":"tools/list","params":{}}' \
| uv run easy-equities-mcp
Credits
easy-equities-clientby Dean Malan — the library this server wraps.- Model Context Protocol by Anthropic.
License
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。