How do I install MCP Server for Chronulus?
You can install it via `pip install chronulus-mcp`, build a Docker image from the GitHub repo, or run it with `uvx chronulus-mcp` (requires `uv`).
@ChronulusAI
基本信息
MCP Server for Chronulus AI Forecasting and Prediction Agents
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"chronulus-mcp": {
"command": "docker",
"args": [
"build",
".",
"-t",
"chronulus-mcp"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
MCP Server for Chronulus is a server that connects Claude desktop to Chronulus AI’s forecasting and prediction agents, allowing users to interact with these agents directly through Claude’s chat interface.
Install the server via pip install chronulus-mcp, Docker, or uvx chronulus-mcp. Add a configuration entry to your Claude Desktop config file (claude_desktop_config.json) with the CHRONULUS_API_KEY environment variable set. Optionally, pair it with other MCP servers like filesystem and fetch for expanded capabilities.
You can install it via `pip install chronulus-mcp`, build a Docker image from the GitHub repo, or run it with `uvx chronulus-mcp` (requires `uv`).
Add a server entry named `chronulus-agents` to your `claude_desktop_config.json`, set the command (e.g., `uvx`), and provide the `CHRONULUS_API_KEY` environment variable.
Use the absolute path to `python` or `uvx` in the configuration. For `uvx` errors, install `uv` first (see Astral’s installation guide).
Yes. The README shows an example config that includes `filesystem` and `fetch` servers alongside the Chronulus agent.
Yes. When using Chronulus, prefer input field types like `TextFromFile`, `PdfFromFile`, and `ImageFromFile` over scanning files directly. When plotting forecasts, always include the Chronulus‑provided forecast explanation below the plot.
不止于 CSS

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.
YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context
Hindsight: Agent Memory That Learns

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.
评论