curistat-mcp
Futures volatility intelligence MCP server for ES, NQ, and related products. Provides forecasts, regime detection, rare signals, and research tools for AI trading agents.
README
Curistat MCP Server
Futures-specific volatility intelligence for AI agents via the Model Context Protocol.
The first MCP server dedicated to futures volatility analytics. Provides forecasts, regime detection, rare signals, directional bias, and research tools for ES, NQ, and related products.
Quick Start
1. Install
pip install curistat-mcp
2. Get a Curistat API key
Sign up at curistat.com/developer and generate an API key.
3. Configure Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"curistat": {
"command": "python",
"args": ["-m", "curistat_mcp"],
"env": {
"CURISTAT_API_KEY": "cst_agent_your_key_here"
}
}
}
}
Restart Claude Desktop. You can now ask Claude questions like:
- "What's the volatility forecast for ES today?"
- "Are there any rare signals firing for NQ?"
- "Show me the economic calendar for next week"
- "Find historical days similar to today for ES"
Available Tools
Core Intelligence
| Tool | Description |
|---|---|
get_forecast_today |
Daily volatility forecast (1-10 rating) with expected move ranges |
get_forecast_week |
5-day forward volatility forecast |
get_signals |
Scan all 24 rare volatility signals |
get_direction |
Directional bias (17-component aggregate) |
get_session_plan |
Full session planner with trade setups |
Regime
| Tool | Description |
|---|---|
get_regime |
CRC composite (0-100, 5 bands) |
get_pulse |
Market conditions snapshot |
Research
| Tool | Description |
|---|---|
get_calendar |
Economic calendar with vol impact estimates |
get_event_impact |
Historical vol analysis around specific events |
get_similar_days |
Historical analog day lookup |
Supported Products
ES, NQ, MES, MNQ, SPX, SPY, QQQ
Agent Framework Integration
CrewAI
from crewai import Agent
from crewai_tools import MCPTool
curistat_tools = MCPTool(
server_command="python",
server_args=["-m", "curistat_mcp"],
server_env={"CURISTAT_API_KEY": "cst_agent_..."},
)
analyst = Agent(
role="Futures Volatility Analyst",
tools=[curistat_tools],
goal="Analyze market conditions and provide trading intelligence",
)
LangChain
from langchain_mcp import MCPToolkit
toolkit = MCPToolkit(
server_command="python",
server_args=["-m", "curistat_mcp"],
server_env={"CURISTAT_API_KEY": "cst_agent_..."},
)
tools = toolkit.get_tools()
Direct stdio (any MCP client)
CURISTAT_API_KEY=cst_agent_... python -m curistat_mcp
The server communicates via stdio using the MCP protocol.
Environment Variables
| Variable | Required | Default | Description |
|---|---|---|---|
CURISTAT_API_KEY |
Yes | -- | Your Curistat Developer API key |
CURISTAT_API_URL |
No | https://api.curistat.com |
API base URL |
Rate Limits
Rate limits are enforced by your API key tier, not by the MCP server. The server is a thin client that proxies requests to the Curistat API.
| Tier | Requests/min | Requests/day |
|---|---|---|
| Free | 10 | 100 |
| Pro | 60 | 5,000 |
| Agent | 120 | 50,000 |
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.