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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.