Chronulus MCP

Connect Chronulus AI Forecasting & Prediction Agents to Claude via the Model Context Protocol.

View on GitHub Visit Website

103

Stars

Forks

103

Watchers

Issues

Chronulus MCP provides an MCP server enabling Claude users to interact with Chronulus AI forecasting and prediction agents. It allows seamless integration through multiple methods including pip, docker, and uvx, offering flexibility in deployment. The tool is designed to fit into the Claude desktop client's model context protocol configuration, streamlining the usage of Chronulus AI’s predictive capabilities in various workflows.

Key Features

Provides an MCP server for Chronulus AI agents

Integrates with the Claude desktop application

Supports installation via pip, GitHub, and docker

Enables configuration through claude_desktop_config.json

Allows environment variable setup for secure API key management

Compatible with third-party MCP servers such as filesystem and fetch

Offers uvx-based automated setup

Works on macOS and Windows

Flexible deployment options for local or containerized environments

Detailed user guidance for troubleshooting common issues

Use Cases

Connecting Chronulus AI agents to Claude for advanced forecasting

Running custom AI predictions within Claude chat sessions

Deploying Chronulus MCP on desktops for business intelligence workflows

Combining Chronulus agents with third-party servers for enhanced model context

Facilitating seamless AI experimentation within the Claude environment

Streamlining setup for organizations needing controlled forecasting integrations

Using dockerized Chronulus MCP for reproducible deployments

Automating configuration with uvx for easy scaling

Customizing user experiences in Claude with predictive AI capabilities

Enabling researchers to access Chronulus AI without complex manual integration

README

Quickstart: Claude for Desktop

Install

Claude for Desktop is currently available on macOS and Windows.

Install Claude for Desktop here

Configuration

Follow the general instructions here to configure the Claude desktop client.

You can find your Claude config at one of the following locations:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json

Then choose one of the following methods that best suits your needs and add it to your claude_desktop_config.json

(Option 1) Install release from PyPI

bash

pip install chronulus-mcp

(Option 2) Install from Github

bash

git clone https://github.com/ChronulusAI/chronulus-mcp.git
cd chronulus-mcp
pip install .

json

{
  "mcpServers": {
    "chronulus-agents": {
      "command": "python",
      "args": ["-m", "chronulus_mcp"],
      "env": {
        "CHRONULUS_API_KEY": "<YOUR_CHRONULUS_API_KEY>"
      }
    }
  }
}

Note, if you get an error like "MCP chronulus-agents: spawn python ENOENT", then you most likely need to provide the absolute path to python. For example /Library/Frameworks/Python.framework/Versions/3.11/bin/python3 instead of just python

Here we will build a docker image called 'chronulus-mcp' that we can reuse in our Claude config.

bash

git clone https://github.com/ChronulusAI/chronulus-mcp.git
cd chronulus-mcp
 docker build . -t 'chronulus-mcp'

In your Claude config, be sure that the final argument matches the name you give to the docker image in the build command.

json

{
  "mcpServers": {
    "chronulus-agents": {
      "command": "docker",
      "args": ["run", "-i", "--rm", "-e", "CHRONULUS_API_KEY", "chronulus-mcp"],
      "env": {
        "CHRONULUS_API_KEY": "<YOUR_CHRONULUS_API_KEY>"
      }
    }
  }
}

uvx will pull the latest version of chronulus-mcp from the PyPI registry, install it, and then run it.

json

{
  "mcpServers": {
    "chronulus-agents": {
      "command": "uvx",
      "args": ["chronulus-mcp"],
      "env": {
        "CHRONULUS_API_KEY": "<YOUR_CHRONULUS_API_KEY>"
      }
    }
  }
}

Note, if you get an error like "MCP chronulus-agents: spawn uvx ENOENT", then you most likely need to either:

install uv or
Provide the absolute path to uvx. For example /Users/username/.local/bin/uvx instead of just uvx

Additional Servers (Filesystem, Fetch, etc)

In our demo, we use third-party servers like fetch and filesystem.

For details on installing and configure third-party server, please reference the documentation provided by the server maintainer.

Below is an example of how to configure filesystem and fetch alongside Chronulus in your claude_desktop_config.json:

json

{
  "mcpServers": {
    "chronulus-agents": {
      "command": "uvx",
      "args": ["chronulus-mcp"],
      "env": {
        "CHRONULUS_API_KEY": "<YOUR_CHRONULUS_API_KEY>"
      }
    },
    "filesystem": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-filesystem",
        "/path/to/AIWorkspace"
      ]
    },
    "fetch": {
      "command": "uvx",
      "args": ["mcp-server-fetch"]
    }
  }
}

Claude Preferences

To streamline your experience using Claude across multiple sets of tools, it is best to add your preferences to under Claude Settings.

You can upgrade your Claude preferences in a couple ways:

From Claude Desktop: Settings -> General -> Claude Settings -> Profile (tab)
From claude.ai/settings: Profile (tab)

Preferences are shared across both Claude for Desktop and Claude.ai (the web interface). So your instruction need to work across both experiences.

Below are the preferences we used to achieve the results shown in our demos:

## Tools-Dependent Protocols
The following instructions apply only when tools/MCP Servers are accessible.

### Filesystem - Tool Instructions
- Do not use 'read_file' or 'read_multiple_files' on binary files (e.g., images, pdfs, docx) .
- When working with binary files (e.g., images, pdfs, docx) use 'get_info' instead of 'read_*' tools to inspect a file.

### Chronulus Agents - Tool Instructions
- When using Chronulus, prefer to use input field types like TextFromFile, PdfFromFile, and ImageFromFile over scanning the files directly.
- When plotting forecasts from Chronulus, always include the Chronulus-provided forecast explanation below the plot and label it as Chronulus Explanation.

Star History

Repository Owner

ChronulusAI

Organization

Repository Details

Language Python

Default Branch main

Size 94 KB

Contributors 1

License MIT License

MCP Verified Nov 12, 2025

Programming Languages

Python

51.79%

HTML

31.43%

JavaScript

15.5%

Dockerfile

1.27%

Related MCPs

Discover similar Model Context Protocol servers

MCP Weather Server

Provides weather forecasts to LLMs via the Model Context Protocol.

MCP Weather Server enables large language models to access real-time, accurate weather forecasts by interfacing with the AccuWeather API. It offers both hourly and daily weather data, supporting metric and imperial units, and can be seamlessly integrated with MCP-compatible clients like Claude Desktop or supergateway. The server provides tools for retrieving weather based on location and settings, with robust configuration options. It is designed for straightforward deployment using Node.js and environment-configured API keys.

⭐ 27
MCP
TimLukaHorstmann/mcp-weather

OpenAI MCP Server

Bridge between Claude and OpenAI models using the MCP protocol.

OpenAI MCP Server enables direct querying of OpenAI language models from Claude via the Model Context Protocol (MCP). It provides a configurable Python server that exposes OpenAI APIs as MCP endpoints. The server is designed for seamless integration, requiring simple configuration updates and environment variable setup. Automated testing is supported to verify connectivity and response from the OpenAI API.

⭐ 77
MCP
pierrebrunelle/mcp-server-openai

Codex MCP Server

An MCP-compatible server delivering enriched blockchain data for AI models.

Codex MCP Server implements the Model Context Protocol to provide enriched blockchain data from Codex. It is compatible with MCP clients such as Claude Desktop and Claude CLI, allowing seamless integration in AI workflows that require blockchain context. Users can run the server locally or via npx, and configure it for various MCP-compatible tools using their Codex API key.

⭐ 20
MCP
Codex-Data/codex-mcp

Coincap MCP

Query live cryptocurrency data through Coincap's public API for desktop AI tools.

Coincap MCP provides seamless access to cryptocurrency market data from Coincap's public API without requiring API keys or registration. Designed to integrate with Claude Desktop using the Model Context Protocol (MCP), it enables users to query crypto asset prices, market capitalization, and a list of available assets. Installation and configuration are streamlined through Smithery or direct setup. The tool includes sample prompts and exposes specialized tools for crypto price lookup and asset listing.

⭐ 89
MCP
QuantGeekDev/coincap-mcp

Intruder MCP

Enable AI agents to control Intruder.io via the Model Context Protocol.

Intruder MCP allows AI model clients such as Claude and Cursor to interactively control the Intruder vulnerability scanner through the Model Context Protocol. It can be deployed using smithery, locally with Python, or in a Docker container, requiring only an Intruder API key for secure access. The tool provides integration instructions tailored for MCP-compatible clients, streamlining vulnerability management automation for AI-driven workflows.

⭐ 21
MCP
intruder-io/intruder-mcp

Dune Analytics MCP Server

Bridge Dune Analytics data seamlessly to AI agents via a Model Context Protocol server.

Dune Analytics MCP Server provides a Model Context Protocol-compliant server that allows AI agents to access and interact with Dune Analytics data. It exposes tools to fetch the latest results of Dune queries and execute arbitrary queries, returning results in CSV format. The server is easily deployable, supports integration with platforms like Claude Desktop, and requires a Dune Analytics API key for operation.

⭐ 31
MCP
kukapay/dune-analytics-mcp

View all Alternatives

Didn't find tool you were looking for?

Search AI Tools

Chronulus MCP

Key Features

Use Cases

README

Quickstart: Claude for Desktop

Install

Configuration

Additional Servers (Filesystem, Fetch, etc)

Claude Preferences

Star History

Repository Owner

Repository Details

Programming Languages

Tags

Related MCPs