# Genius Decision

> Genius Decision is an open-source MCP server for analytics and data. A public decision-modelling engine for agents: demo runs, opportunities and contributions. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Open source
- **Platforms:** API, Web, self-hosted
- **Website:** https://geniusdecision.app/agents
- **Repository:** https://github.com/pedrosalvadeo/genius-decision-open
- **MCP Registry name:** io.github.pedrosalvadeo/genius-decision
- **Categories:** analytics and data, AI models and LLM tooling
- **Listing updated:** 2026-11-15

## About

Genius Decision, whose site is in Spanish, publishes a decision-modelling engine and a capsule of mission, mathematics, code and local execution. The MCP server is aimed at agents rather than end users. Its public demo needs no sign-in and discovers get_capabilities, find_opportunities, read_demo_result and run_demo; submit_contribution lets an agent drop tests, models or evidence into a public inbox without a GitHub account. Receipt of a file does not mean it will be merged.

The demo runs the same engine in an isolated space on synthetic examples only (hours-known, hours-unknown, fdq-frontier, fdq-selector), and saved results include one with known values and one with unknown values. Operating your own space takes an agent credential with limited permissions. The site also lists ten collaboration opportunities with evidence and acceptance criteria, such as connecting observations to predictions or auditing the mathematics and code.

The repository code and documentation are Apache-2.0 and include a Python CLI, with Python 3.11+ on Linux required locally.

## Features

- **Public synthetic demo:** Run the engine on fixed synthetic examples without registration.
- **Readable results:** Saved runs keep transport, execution, evidence, decisions and quality.
- **Opportunity catalogue:** Ten contribution tasks with evidence and acceptance criteria.
- **Contribution inbox:** Submit tests, models and evidence by HTTP or MCP.
- **Open capsule:** Mission, mathematics and code in an Apache-2.0 repository.
- **Scoped credentials:** Agent credentials with limited permissions for your own space.

## Good for

- Try the engine on a synthetic example
- Pick an open task to contribute to
- Audit the mathematics or code
- Link observations to predictions

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http genius-decision https://geniusdecision.app/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://geniusdecision.app/mcp
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "genius-decision": {
      "url": "https://geniusdecision.app/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "genius-decision": {
      "type": "http",
      "url": "https://geniusdecision.app/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "genius-decision": {
      "serverUrl": "https://geniusdecision.app/mcp"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "genius-decision": {
      "type": "http",
      "url": "https://geniusdecision.app/mcp"
    }
  }
}
```

## Tools

- `get_capabilities`: Describes what the server and engine can do.
- `find_opportunities`: Lists contribution opportunities.
- `read_demo_result`: Reads a saved demo result.
- `run_demo`: Runs a synthetic demo example.
- `submit_contribution`: Submits tests, models or evidence to the public inbox.

## FAQ

### Do I need to register to try it?

No. The demo needs no sign-in and uses synthetic data only.

### Can I upload my own data to the demo?

No. It accepts only the listed synthetic examples.

### Does submitting a file get it merged?

No. Receiving a file does not mean it is accepted into the engine.

### What licence is the code?

Apache-2.0 for the original code and documentation.

### Is Genius Decision free?

Yes. Genius Decision is open source, so you can use and self-host it for free.

### How do I add Genius Decision to Claude Code?

Run this command in your terminal: claude mcp add --transport http genius-decision https://geniusdecision.app/mcp

### What are the best alternatives to Genius Decision?

The closest alternatives to Genius Decision are Agent-Native Analytics, Claude Code Ultimate Guide, Google Ads + Meta Ads + SEO/GEO MCP, Tapetide - Indian Stock Market MCP and World Monitor.

## Alternatives

- [Agent-Native Analytics](https://ai-powered.com/mcp/agent-native-analytics): Agent-Native Analytics is an open-source MCP server for analytics and data.
- [Claude Code Ultimate Guide](https://ai-powered.com/mcp/claude-code-ultimate-guide): Claude Code Ultimate Guide is an open-source MCP server for ai models and llm tooling.
- [Google Ads + Meta Ads + SEO/GEO MCP](https://ai-powered.com/mcp/google-ads-meta-ads-seo-geo-mcp): Google Ads + Meta Ads + SEO/GEO MCP is a freemium MCP server for marketing and seo.
- [Tapetide - Indian Stock Market MCP](https://ai-powered.com/mcp/tapetide-indian-stock-market-mcp): Tapetide - Indian Stock Market MCP is a freemium MCP server for finance and payments.
- [World Monitor](https://ai-powered.com/mcp/world-monitor): World Monitor is a freemium MCP server for analytics and data.
- [CompanyData](https://ai-powered.com/mcp/companydata): CompanyData is a paid MCP server for analytics and data.
- [ChartAnt](https://ai-powered.com/mcp/chartant): ChartAnt is a freemium MCP server for design and media.
- [Quantivex Research](https://ai-powered.com/mcp/quantivex-research): Quantivex Research is a free MCP server for finance and payments.

---
Source: https://ai-powered.com/mcp/genius-decision
