mcpField
M
MCP

MCP

Local
github.com/vvalkov1Finance0Updated 74w ago
Repository

About MCP

An MCP server that classifies a crypto asset’s 1-hour price regime as trending or ranging using price data and technical indicators. It can run over HTTP or standard input/output for supported MCP clients.

Key features

  1. 01Classify trending or ranging regimes
  2. 02Analyze 1-hour crypto charts
  3. 03Use price data and technical indicators
  4. 04Run over HTTP or standard input/output

Use cases

  1. 01Assess a crypto asset’s current price regime
  2. 02Add technical-regime checks to an MCP workflow

MCP support

Exposes a crypto price-regime analysis tool to MCP clients. It supports an HTTP endpoint at /mcp or standard input/output, depending on configuration.

#crypto#trading#technical-analysis

Configuration

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

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Overview

MCP Server that provides a tool to determine whether the price of a given crypto asset is in a trending or ranging regime on the 1-hour chart, using both price data and technical analysis (TA) indicators.

Setup

If you want to use the server inside Cursor or VSC, you can set RUN_HTTP_SERVER to true in the environment variables. Then run the project using one of these options:

  1. Docker: docker compose up --build
  2. NPM: npm run build npm run start

The server is running on port 3100. You can connect to it in your MCP client using the URL: "http://localhost:3100/mcp".

Example configuration for VSC (mcp.json):

{ "servers": { "my-mcp-server-a7160f39": { "url": "http://localhost:3100/mcp" } } }

Otherwise, if you want to use Claude Desktop, you should set RUN_HTTP_SERVER to false. Run the following command to build the docker image locally:

docker build -t mcp-hyperion .

Then you should put this configuration into claude_desktop_config.json:

"hyperion": { "command": "docker", "args": [ "run", "-i", "--rm", "-p", "3100:3100", "-e", "COINMARKETCAP_API_KEY", "-e", "TAAPI_API_KEY", "-e", "ANTHROPIC_API_KEY", "-e", "RUN_HTTP_SERVER", "mcp-hyperion" ], "env": { "COINMARKETCAP_API_KEY": "your_api_key", "TAAPI_API_KEY": "your_api_key", "ANTHROPIC_API_KEY": "your_api_key", "RUN_HTTP_SERVER": "false" } }

Environment variables

You need to set the described environment variables in .env file in the root directory:

COINMARKETCAP_API_KEY - Your coinmarketcap.com API key TAAPI_API_KEY - Your taapi.io API key ANTHROPIC_API_KEY - Your anthropic API key RUN_HTTP_SERVER - Use "true" or "false". Whether to start a HTTP server, if "false", the MCP will use the standard input/output (Claude Desktop Support)

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.