> ## Documentation Index
> Fetch the complete documentation index at: https://docs.pond3r.xyz/llms.txt
> Use this file to discover all available pages before exploring further.

# MCP Server

> Connect your AI agent directly to Pond3r datasets using the Model Context Protocol

## Overview

Pond3r provides a [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) server that lets AI agents query curated crypto datasets directly. The server uses **Streamable HTTP transport**, so it works with Claude Desktop, Claude Code, Cursor, and any MCP-compatible client.

## Getting Your API Key

<Steps>
  <Step title="Create an account">
    Sign up at [makeit.pond3r.xyz](https://makeit.pond3r.xyz) if you haven't already.
  </Step>

  <Step title="Generate an API key">
    Go to [makeit.pond3r.xyz/api-keys](https://makeit.pond3r.xyz/api-keys) and generate a new key.

    <Warning>
      Keep your API key secure. Never expose it in client-side code or public repositories.
    </Warning>
  </Step>
</Steps>

## Setup with Claude Code

Run this command in your terminal to add the Pond3r MCP server:

```bash theme={null}
claude mcp add pond3r-data \
  --transport http \
  https://mcp.pond3r.xyz/mcp \
  --header "Authorization: Bearer your_api_key_here"
```

The tools will be available immediately in your Claude Code session.

## Setup with Claude Desktop

Add the following to your Claude Desktop MCP configuration file (`claude_desktop_config.json`):

```json theme={null}
{
  "mcpServers": {
    "pond3r": {
      "type": "http",
      "url": "https://mcp.pond3r.xyz/mcp",
      "headers": {
        "Authorization": "Bearer your_api_key_here"
      }
    }
  }
}
```

Restart Claude Desktop and the Pond3r tools will be available in your conversations.

## Setup with Cursor

In Cursor, go to **Settings** > **MCP Servers** and add a new server:

* **URL**: `https://mcp.pond3r.xyz/mcp`
* **Headers**: `Authorization: Bearer your_api_key_here`

## Setup with Other Clients

For any MCP-compatible client that supports Streamable HTTP transport, send POST requests to:

```
https://mcp.pond3r.xyz/mcp
```

Pass your API key as a Bearer token in the `Authorization` header:

```
Authorization: Bearer your_api_key_here
```

## Available Tools

Once connected, your AI agent has access to three tools:

| Tool            | Description                                             |
| --------------- | ------------------------------------------------------- |
| `list_datasets` | List all available datasets and their tables            |
| `get_schema`    | Get column names, types, and descriptions for a dataset |
| `query`         | Execute a read-only SQL query against a dataset         |

The agent will automatically discover schemas and available data — you just need to ask your question in natural language.

### Query Tool

The `query` tool executes read-only SQL against Pond3r datasets. A few things to note:

* **SELECT only** — write operations are not allowed.
* **Use bare table names** — e.g. `SELECT * FROM stablecoin_yields`, not fully qualified paths.
* **Results are capped at 10,000 rows** — use `LIMIT` or `WHERE` filters for large datasets.
* **Cost is estimated before execution** — queries that exceed your tier limits are rejected before running.

## Available Datasets

The MCP server provides access to the following curated datasets:

### Prediction Markets

<AccordionGroup>
  <Accordion title="polymarket — Polymarket markets and tokens">
    Periodic snapshots of Polymarket prediction markets with prices, volume, liquidity, and resolution status. Includes a pre-computed view linking markets to CLOB token IDs for crypto up/down markets.

    **Tables**: `polymarket_trades`, `polymarket_resolutions`, `polymarket_markets`, `polymarket_market_tokens`

    **Best for**: Market analysis, resolution tracking, crypto derivatives research
  </Accordion>

  <Accordion title="crypto_trades — Crypto market trades">
    Enriched Polymarket crypto 5m/15m market trades with pre-computed price, size, side, and market timing. Filtered to BTC, ETH, SOL, XRP up/down markets only.

    **Tables**: `crypto_trades`

    **Best for**: Trade flow analysis, price discovery, market microstructure
  </Accordion>

  <Accordion title="crypto_market_resolutions — Resolved crypto markets">
    One row per resolved crypto 5m/15m market with outcome and metadata. Includes volume, liquidity, and resolution timestamps.

    **Tables**: `crypto_market_resolutions`

    **Best for**: Backtesting strategies, outcome prediction, market efficiency analysis
  </Accordion>

  <Accordion title="market_summary — Per-market aggregated stats">
    One row per crypto 5m/15m market with aggregated trade stats, price stats, resolution outcome, and orderbook stats. Primary view for strategy backtests.

    **Tables**: `market_summary`

    **Best for**: Strategy development, market behavior analysis, performance research
  </Accordion>

  <Accordion title="orderbook_features — Orderbook time-series">
    Enriched orderbook snapshots with time-series features (changes between consecutive snapshots). Built with LAG window functions for detecting liquidity changes.

    **Tables**: `orderbook_features`

    **Best for**: Liquidity analysis, market making research, microstructure studies
  </Accordion>

  <Accordion title="cross_timeframe_signals — 5m→15m predictions">
    For each resolved 15-minute market, counts how many overlapping 5-minute markets resolved up vs down, and whether this predicted the 15-minute outcome.

    **Tables**: `cross_timeframe_signals`

    **Best for**: Multi-timeframe analysis, signal generation, predictive modeling
  </Accordion>

  <Accordion title="streak_features — Sequential patterns">
    Sequential market patterns tracking consecutive same-outcome streaks and whether they break. Useful for mean-reversion studies.

    **Tables**: `streak_features`

    **Best for**: Pattern recognition, momentum/reversion analysis, sequence modeling
  </Accordion>
</AccordionGroup>

### DeFi Yields & Lending

<AccordionGroup>
  <Accordion title="stablecoin_yields — Curated stablecoin yields">
    Hourly snapshots of stablecoin DeFi yields across lending protocols. TIME-SERIES TABLE with multiple snapshot rows per pool — always use deduplication.

    **Tables**: `stablecoin_yields`

    **Best for**: Yield farming, protocol comparison, APY optimization

    <Warning>
      This is a time-series table. Always use `QUALIFY ROW_NUMBER() OVER (PARTITION BY blockchain, protocol_name, token_symbol ORDER BY data_collection_timestamp DESC) = 1` to get the latest snapshot per pool.
    </Warning>
  </Accordion>

  <Accordion title="yield_pool_features — Pool yields with rolling stats">
    Daily aggregated pool yields enriched with 7d/30d rolling stats, momentum indicators, spike detection, and rankings. Built from yield\_pool\_daily.

    **Tables**: `yield_pool_features`

    **Best for**: Trend analysis, risk-adjusted returns, yield stability assessment
  </Accordion>

  <Accordion title="morpho_market_features — Morpho market analysis">
    Daily Morpho individual market data enriched with rolling stats, utilization trends, and rankings. Includes supply APY, utilization, and flow metrics.

    **Tables**: `morpho_market_features`

    **Best for**: Morpho-specific strategies, capital efficiency research, utilization analysis
  </Accordion>

  <Accordion title="morpho_vault_features — Morpho vault performance">
    Daily Morpho vault data enriched with APY features, actual share price returns, and rankings. Tracks net APY after fees and cumulative returns.

    **Tables**: `morpho_vault_features`

    **Best for**: Vault comparison, return tracking, fee impact analysis
  </Accordion>

  <Accordion title="aave_rate_features — Aave cross-chain rates">
    Daily Aave rates enriched with rolling stats and cross-chain ranking. Identifies best chains per token and arbitrage opportunities.

    **Tables**: `aave_rate_features`

    **Best for**: Cross-chain optimization, rate comparison, chain selection
  </Accordion>
</AccordionGroup>

## Example Conversations

Once the MCP server is connected, you can ask your AI agent questions like:

### Prediction Markets

```
What's the win rate for BTC 5-minute up markets in the last week?
```

```
Show me the top 10 most active Polymarket traders by volume.
```

```
Find 15-minute markets where all three 5-minute sub-markets agreed on direction.
```

### DeFi Yields

```
What are the top 5 stablecoin yields on Ethereum right now?
```

```
Compare USDC yields across Aave, Morpho, and other protocols on Arbitrum.
```

```
Show me pools with APY > 10% and low volatility (cv_30d < 0.3).
```

The agent will use the `list_datasets` and `get_schema` tools to understand what's available, then write and execute SQL via the `query` tool.

## Troubleshooting

<AccordionGroup>
  <Accordion title="Connection refused or timeout">
    Make sure your API key is valid and correctly set. Check that your client is sending the `Authorization` header with every request.
  </Accordion>

  <Accordion title="Query rejected: use simple table names">
    The server requires bare table names (e.g. `stablecoin_yields`). Do not include project or dataset prefixes in your SQL.
  </Accordion>

  <Accordion title="Usage limit exceeded">
    You've hit your daily or monthly spend cap. Wait for the limit to reset or upgrade your plan for higher limits.
  </Accordion>
</AccordionGroup>