Mirobody
Your Data, Your AI — Health, Finance & More. Open Source, Privacy-First.
What is Mirobody?
Mirobody is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to your data, your ai — health, finance & more. open source, privacy-first.
Your Data, Your AI — Health, Finance & More. Open Source, Privacy-First.
This server falls under the Data Science & ML category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Your Data, Your AI — Health, Finance & More. Open Source, Pr
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx mirobodyConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Mirobody
Mirobody is an open-source, privacy-first personal data platform that lets you store and query health and financial data entirely under your own control. It integrates with 300+ wearables and Apple Health using FHIR standards, and exposes a drop-in MCP endpoint so AI assistants can securely access your personal health indicators, run code in a sandbox, manage files, and generate charts — without sending raw data to third-party cloud services. Individuals and health-tech developers use it to build AI-driven personal health dashboards where the model and the data both stay local.
Prerequisites
- Docker and Docker Compose installed
- Git with Git LFS (run: git lfs install)
- An API key for OpenRouter (required for the DeepAgent) and optionally OpenAI or Google AI
- Python 3.10+ if developing locally without Docker
- An MCP client such as Claude Desktop
Clone the repository with Git LFS
Mirobody uses Git LFS for large assets. Install Git LFS first, then clone the repository.
git lfs install
git clone https://github.com/thetahealth/mirobody.git
cd mirobodyDeploy with Docker (recommended)
Run the included deploy script which generates the .env file with a CONFIG_ENCRYPTION_KEY, starts Postgres and Redis, and launches the Mirobody API on port 18080.
./deploy.shConfigure API keys and settings
The deploy script generates a config file. Edit it to add your AI provider keys and timezone. The OPENROUTER_API_KEY is required for the multi-tool DeepAgent; others are optional.
# Edit config.{env}.yaml and set:
# OPENROUTER_API_KEY: <your-openrouter-key>
# OPENAI_API_KEY: <optional>
# GOOGLE_API_KEY: <optional>
# DEFAULT_TIMEZONE: America/New_York
# MCP_PUBLIC_URL: http://localhost:18080 # or your remote URLVerify the server is running
Open a browser or curl the health endpoint to confirm Mirobody is up. You can also log in with the demo credentials to explore the interface before connecting your own data.
curl http://localhost:18080/health
# Demo login: [email protected] / 777777Configure your MCP client
Add the Mirobody MCP endpoint to your MCP client. The server uses HTTP transport, so provide the URL of your running instance.
{
"mcpServers": {
"mirobody": {
"url": "http://localhost:18080/mcp"
}
}
}Connect your health data sources
In the Mirobody web UI at http://localhost:18080, connect your wearables (Apple Health, Garmin, Fitbit, etc.) or upload FHIR-formatted health records. Once connected, the data becomes queryable through the MCP tools.
Mirobody Examples
Client configuration
MCP client configuration for a locally running Mirobody instance.
{
"mcpServers": {
"mirobody": {
"url": "http://localhost:18080/mcp"
}
}
}Prompts to try
Example prompts once your health data is connected and the MCP server is running.
- "Show me my average resting heart rate over the past 30 days and plot a trend chart."
- "What were my sleep duration and quality scores this week compared to last week?"
- "Summarize my step count and active calories burned for each day this month."
- "Are there any FHIR observations in my records flagged as outside normal range?"
- "Write a Python script to analyze my VO2 max trend and save the chart to a file."Troubleshooting Mirobody
Deploy script fails or containers do not start
Ensure Docker Desktop is running and Git LFS is installed before cloning. Run 'docker compose logs' to see error details. Common causes are missing LFS files or a port conflict on 18080.
DeepAgent fails with model errors
OPENROUTER_API_KEY is required for the DeepAgent. Confirm the key is set in your config.{env}.yaml and that the file was reloaded after editing (restart the containers with 'docker compose restart').
MCP client cannot reach the server
Verify MCP_PUBLIC_URL in your config matches the URL your client uses. For remote deployments, ensure TLS is configured and the port is open in firewall rules. For local use, confirm the container is binding to 0.0.0.0 not 127.0.0.1.
Frequently Asked Questions about Mirobody
What is Mirobody?
Mirobody is a Model Context Protocol (MCP) server that your data, your ai — health, finance & more. open source, privacy-first. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Mirobody?
Follow the installation instructions on the Mirobody GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Mirobody?
Mirobody works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Mirobody free to use?
Yes, Mirobody is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.
Mirobody Alternatives — Similar Data Science & ML Servers
Looking for alternatives to Mirobody? Here are other popular data science & ml servers you can use with Claude, Cursor, and VS Code.
Ultrarag
★ 5.6kA Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
RocketRide
★ 3.1k📇 🏠 - MCP server that exposes RocketRide AI pipelines as t
Aix Db
★ 2.1kAix-DB 基于 LangChain/LangGraph 框架，结合 MCP Skills 多智能体协作架构，实现自然语言到数据洞察的端到端转换。
NeMo Data Designer
★ 1.9k🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.
PaperBanana
★ 1.7kOpen source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.
MiniMax
★ 1.5kBridges MiniMax AI capabilities to the Model Context Protocol, enabling AI agents to perform image understanding, text-to-image generation, and speech synthesis. It provides a standardized interface for accessing MiniMax's core tools via JSON-RPC.
Browse More Data Science & ML MCP Servers
Explore all data science & ml servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Mirobody in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Mirobody?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.