# Indigo Protocol MCP

> Use this tool when you need to access Indigo Protocol data, such as iAsset prices, CDP/loan analytics, and protocol metrics, and integrate it with LLM agents via the Model Context Protocol. It solves problems related to data access, analytics, and integration, and provides inputs such as natural language queries and outputs like real-time data and analytics. Use it in contexts where you need to fetch, analyze, or visualize Indigo Protocol data, such as trading, investing, or research.

Canonical page: https://skillsregistry.net/skills/indigoprotocol-indigo-mcp  
JSON: https://api.skillsregistry.net/v1/skills/indigoprotocol-indigo-mcp

## Description

# Indigo MCP


MCP server for [Indigo Protocol](https://indigoprotocol.io/) — exposes Indigo iAsset data, prices, and CDP/loan analytics to LLM agents via the [Model Context Protocol](https://modelcontextprotocol.io/).

## Features

- Real-time iAsset prices (iUSD, iBTC, iETH, iSOL)
- ADA and INDY token price feeds
- CDP/loan browsing with pagination and filtering
- Owner lookup by payment key hash or bech32 address
- CDP health analysis with collateral ratio and liquidation risk status
- Stability pool state and account queries
- INDY staking positions and manager state
- Protocol analytics: TVL, APR rewards, DEX yields, aggregated stats
- Governance: protocol parameters, polls, temperature checks
- Redemption order book and queue aggregation
- DEX proxy: Steelswap swaps, Iris liquidity pools, Blockfrost balances
- CDP liquidation, redemption, freeze, and merge operations
- Leveraged CDP opening via LRP positions
- LRP (Limit Redemption Protocol) position management
- Oracle interest rate feeding and initialization
- Stability pool request processing and cancellation
- Staking reward distribution
- Collector UTXOs, IPFS storage and retrieval

## Quick Start

Install globally:

```bash
npm install -g @indigoprotocol/indigo-mcp
```

Or run directly with npx (no install needed):

```bash
npx @indigoprotocol/indigo-mcp
```

### Docker

```bash
docker build -t indigo-mcp .
docker run -i indigo-mcp
```

### HTTP Transport (Remote)

The server supports HTTP transport for remote/hosted deployments:

```bash
MCP_TRANSPORT=http PORT=3000 npx @indigoprotocol/indigo-mcp
```

This starts an HTTP server with:
- `POST /mcp` — MCP endpoint (Streamable HTTP with SSE)
- `GET /health` — Health check

## Configuration

> **Note:** `BLOCKFROST_API_KEY` is required for write operations (transaction building). Read-only tools work without it. Get a free key at [blockfrost.io](https://blockfrost.io/).

### Claude Desktop

Add to `~/Library/Application Support/Claude/claude_desktop_config.json` (macOS) or `%APPDATA%\Claude\claude_desktop_config.json` (Windows):

```json
{
  "mcpServers": {
    "indigo": {
      "command": "npx",
      "args": ["-y", "@indigoprotocol/indigo-mcp"],
      "env": {
        "INDEXER_URL": "https://analytics.indigoprotocol.io/api/v1",
        "BLOCKFROST_API_KEY": "your-blockfrost-project-id"
      }
    }
  }
}
```

### Claude Code (CLI)

Add to `~/.claude/settings.json` or `.claude/settings.json` in your project:

```json
{
  "mcpServers": {
    "indigo": {
      "command": "npx",
      "args": ["-y", "@indigoprotocol/indigo-mcp"],
      "env": {
        "INDEXER_URL": "https://analytics.indigoprotocol.io/api/v1",
        "BLOCKFROST_API_KEY": "your-blockfrost-project-id"
      }
    }
  }
}
```

### Cursor

Add to `~/.cursor/mcp.json` (global) or `.cursor/mcp.json` (project-level):

```json
{
  "mcpServers": {
    "indigo": {
      "command": "npx",
      "args": ["-y", "@indigoprotocol/indigo-mcp"],
      "env": {
        "INDEXER_URL": "https://analytics.indigoprotocol.io/api/v1",
        "BLOCKFROST_API_KEY": "your-blockfrost-project-id"
      }
    }
  }
}
```

### Windsurf

Add to `~/.codeium/windsurf/mcp_config.json`:

```json
{
  "mcpServers": {
    "indigo": {
      "command": "npx",
      "args": ["-y", "@indigoprotocol/indigo-mcp"],
      "env": {
        "INDEXER_URL": "https://analytics.indigoprotocol.io/api/v1",
        "BLOCKFROST_API_KEY": "your-blockfrost-project-id"
      }
    }
  }
}
```

### Any MCP-Compatible Client

Run the server directly via stdio:

```bash
INDEXER_URL=https://analytics.indigoprotocol.io/api/v1 \
BLOCKFROST_API_KEY=your-blockfrost-project-id \
npx @indigoprotocol/indigo-mcp
```

Or install globally and reference the binary:

```bash
npm install -g @indigoprotocol/indigo-mcp
indigo-mcp
```

For any client that supports MCP over stdio, point it to the `npx @indigoprotocol/indigo-mcp` command with the environment variables above.

## Environment Variables

- `INDEXER_URL` — Indigo analytics API base URL (default: `https://analytics.indigoprotocol.io/api/v1`)
- `BLOCKFROST_API_KEY` — Blockfrost project ID for transaction building (required for write ops)
- `CARDANO_NETWORK` — Cardano network: `mainnet`, `preprod`, or `preview` (default: `mainnet`)
- `MCP_TRANSPORT` — Transport mode: `stdio` or `http` (default: `stdio`)
- `PORT` — HTTP server port when `MCP_TRANSPORT=http` (default: `3000`)

## Example Queries

When connected to an LLM agent, you can ask natural language questions like:

- "What are the current prices of all Indigo iAssets?"
- "What is the price of iUSD right now?"
- "How much is ADA worth in USD?"
- "Show me all iETH CDPs"
- "What CDPs does this address own?" (paste a Cardano address)
- "Analyze the health of my CDPs" (with your address or payment key hash)
- "Are any of my positions at risk of liquidation?"
- "Show me the current stability pool state"
- "What are my stability pool deposits?" (with your address)
- "How much INDY am I staking?" (with your address)
- "What's the current TVL of Indigo?"
- "What APR can I earn on iUSD stability pool?"
- "What are the current governance protocol parameters?"
- "Show me the iUSD redemption queue"
- "Get a Steelswap estimate for swapping 100 ADA to iUSD"
- "What are the current DEX yields for iAsset pairs?"

## Trust

- **Trust score (0–1):** 0.30
- **Verification tier:** unverified
- **Last scanned:** 2026-08-24

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-08-24

## Source

- **Source listing:** [Smithery](https://smithery.ai/server/indigoprotocol/indigo-mcp)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "indigoprotocol-indigo-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/indigoprotocol-indigo-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/indigoprotocol-indigo-mcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt