Coinvest
БесплатноНе проверенLocal MCP server that exposes Liquid Co-Invest's trading data and order tools to a local LLM via a thin proxy.
Описание
Local MCP server that exposes Liquid Co-Invest's trading data and order tools to a local LLM via a thin proxy.
README
A local MCP server that exposes Liquid Co-Invest's trading-data and order tools to a local LLM. It is a thin, generic proxy: it holds no hardcoded tools — on startup it fetches the tool catalog from your Liquid backend and forwards each call there. All reasoning happens in your local agent; Liquid executes the individual tool calls.
Backend dependency. This client talks to the Liquid Co-Invest backend
mcp_apiendpoints (GET /api/mcp/tools,POST /api/mcp/dispatch,GET /api/mcp/guide), which must be deployed and enabled for your user.
What it exposes
Whatever the backend registry advertises — market data, balances, portfolio analytics, order status, and trading (spot, perps, prediction markets, and batch orders, plus cancel / close / set leverage). Because the catalog is fetched live, adding or changing a tool on the backend needs no new release here.
It also exposes the authoritative operating guide as the
coinvest_operating_guide prompt, fetched live from the backend — load it
before driving the tools.
Install
First install uv — this is the only prerequisite.
The uvx command used below ships with uv (it's shorthand for uv tool run),
so there is nothing else to install:
# macOS / Linux
curl -LsSf https://astral.sh/uv/install.sh | sh
# or, with Homebrew
brew install uv
Then install and run straight from the repo — no clone required. uvx fetches
the package from GitHub, builds it in an isolated environment (provisioning a
compatible Python automatically), and runs the coinvest-mcp entry point:
uvx --from git+https://github.com/liquid-public/coinvest-mcp.git coinvest-mcp
The server speaks MCP over stdio, so it's normally launched by your MCP client (see Connect your MCP client) rather than run interactively. The command above is the same one you put in the client config.
Pin to a branch or tag by appending @<ref>:
uvx --from git+https://github.com/liquid-public/coinvest-mcp.git@main coinvest-mcp
To install it once as a persistent tool on your PATH (so the command is just
coinvest-mcp), use uv tool instead:
uv tool install git+https://github.com/liquid-public/coinvest-mcp.git
uv tool upgrade coinvest-mcp # pull a newer version later
[!NOTE]
uvxcaches the build. After the backend ships changes that only affect this client, force a rebuild withuvx --refresh --from git+https://github.com/liquid-public/coinvest-mcp.git coinvest-mcp.
Configuration
| Var | Required | Description |
|---|---|---|
COINVEST_URL |
yes | Base URL of the Co-Invest server, e.g. https://coinvest.liquid.trade |
COINVEST_MCP_TOKEN |
yes | Your MCP token (generate/regenerate it in the Liquid web app) |
COINVEST_READONLY |
no | 1 to hide all write/trading tools |
COINVEST_TIMEOUT |
no | HTTP timeout in seconds (default 30) |
The token can be generated from the Liquid web app (app.liquid.trade).
The token authenticates as you; every call is scoped to your account
server-side. One running server == one Liquid user. The token expires after a
period (default 30 days) of inactivity (it is refreshed on each use); once
expired, requests return 401 and you regenerate it from the Liquid web app.
Connect your MCP client
Point your MCP client at the same uvx command. The client launches the server
on demand and passes configuration through env.
Claude Code (CLI)
claude mcp add coinvest \
--env COINVEST_URL=https://coinvest.liquid.trade \
--env COINVEST_MCP_TOKEN=your-token-here \
-- uvx --from git+https://github.com/liquid-public/coinvest-mcp.git coinvest-mcp
Add --env COINVEST_READONLY=1 for a read-only setup.
Claude Desktop / generic MCP client (JSON)
{
"mcpServers": {
"coinvest": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/liquid-public/coinvest-mcp.git",
"coinvest-mcp"
],
"env": {
"COINVEST_URL": "https://coinvest.liquid.trade",
"COINVEST_MCP_TOKEN": "your-token-here"
}
}
}
}
For a read-only setup, add "COINVEST_READONLY": "1" to env.
[!NOTE] The client must be able to find
uvxon itsPATH. If it can't (common on macOS GUI apps), use the absolute path fromwhich uvxascommand, e.g./opt/homebrew/bin/uvx.
Develop
Clone the repo for local development, then sync and test:
git clone https://github.com/liquid-public/coinvest-mcp.git
cd coinvest-mcp
uv sync
uv run pytest
Run your local checkout directly (point the client at this command to test changes before pushing):
uv run --directory /path/to/coinvest-mcp coinvest-mcp
Safety
The local agent owns risk. Liquid runs no server-side agent for these calls —
there is no automated margin management, invariant enforcement, or liveness
rescue behind them. See the coinvest_operating_guide prompt for the operating
contract.
Установка Coinvest
У этого сервера нет опубликованного пакета — он собирается из исходников. Открой репозиторий и следуй инструкции в README.
▸ github.com/liquid-public/coinvest-mcpFAQ
Coinvest MCP бесплатный?
Да, Coinvest MCP бесплатный — установка в пару кликов через Unyly без оплаты.
Нужен ли API-ключ для Coinvest?
Нет, Coinvest работает без API-ключей и переменных окружения.
Coinvest — hosted или self-hosted?
Self-hosted: сервер запускается локально на твоей машине командой из раздела установки.
Как установить Coinvest в Claude Desktop, Claude Code или Cursor?
Открой Coinvest на unyly.org, выбери вкладку своего клиента (Claude Desktop, Claude Code, Cursor) и нажми Install — конфиг сгенерируется автоматически, без правки JSON.
Похожие MCP
Fetch
Web content fetching and conversion for efficient LLM usage.
AWS KB Retrieval
Retrieval from AWS Knowledge Base using Bedrock Agent Runtime.
автор: modelcontextprotocolSpring AI MCP Server
Provides auto-configuration for setting up an MCP server in Spring Boot applications.
llm-analysis-assistant
A very streamlined mcp client that supports calling and monitoring stdio/sse/streamableHttp, and can also view request responses through the /logs page. It also
автор: xuzexin-hzCompare Coinvest with
Не уверен что выбрать?
Найди свой стек за 60 секунд
Автор?
Embed-бейдж для README
Похожее
Все в категории ai
