Cryo

Cryo MCP

A Model Completion Protocol (MCP) server for the Cryo blockchain data extraction tool.

Cryo MCP allows you to access Cryo's powerful blockchain data extraction capabilities via an API server that implements the MCP protocol, making it easy to query blockchain data from any MCP-compatible client.

For LLM Users: SQL Query Workflow Guide

When using this MCP server to run SQL queries on blockchain data, follow this workflow:

Download data with query_dataset:

Explore schema with get_sql_table_schema:

Run SQL with query_sql:

Alternatively, use the combined approach with query_blockchain_sql:

For a complete working example, see examples/sql_workflow_example.py.

Features

Full Cryo Dataset Access: Query any Cryo dataset through an API server

MCP Integration: Works seamlessly with MCP clients

Flexible Query Options: Support for all major Cryo filtering and output options

Block Range Options: Query specific blocks, latest block, or relative ranges

Contract Filtering: Filter data by contract address

Latest Block Access: Easy access to the latest Ethereum block data

Multiple Output Formats: JSON, CSV, and Parquet support

Schema Information: Get detailed dataset schemas and sample data

SQL Queries: Run SQL queries directly against downloaded blockchain data

Installation (Optional)

This is not required if you will run the tool with uvx directly.

Requirements

Python 3.8+

A working installation of Cryo

Access to an Ethereum RPC endpoint

DuckDB (for SQL query functionality)

Quick Start

Usage with Claude Code

Run claude mcp add for an interactive prompt.

Enter uvx as the command to run.

Enter cryo-mcp --rpc-url <ETH_RPC_URL> [--data-dir <DATA_DIR>] as the args

Alternatively, provide ETH_RPC_URL and CRYO_DATA_DIR as environment variables instead.

New instances of claude will now have access to cryo as configured to hit your RPC endpoint and store data in the specified directory.

Available Tools

Cryo MCP exposes the following MCP tools:

`list_datasets()`

Returns a list of all available Cryo datasets.

Example:

`query_dataset()`

Query a Cryo dataset with various filtering options.

Parameters:

dataset (str): The name of the dataset to query (e.g., 'blocks', 'transactions', 'logs')

blocks (str, optional): Block range specification (e.g., '1000:1010')

start_block (int, optional): Start block number (alternative to blocks)

end_block (int, optional): End block number (alternative to blocks)

use_latest (bool, optional): If True, query the latest block

blocks_from_latest (int, optional): Number of blocks from latest to include

contract (str, optional): Contract address to filter by

output_format (str, optional): Output format ('json', 'csv', 'parquet')

include_columns (list, optional): Columns to include alongside defaults

exclude_columns (list, optional): Columns to exclude from defaults

Example:

`lookup_dataset()`

Get detailed information about a specific dataset, including schema and sample data.

Parameters:

name (str): The name of the dataset to look up

sample_start_block (int, optional): Start block for sample data

sample_end_block (int, optional): End block for sample data

use_latest_sample (bool, optional): Use latest block for sample

sample_blocks_from_latest (int, optional): Number of blocks from latest for sample

Example:

`get_latest_ethereum_block()`

Returns information about the latest Ethereum block.

Example:

SQL Query Tools

Cryo MCP includes several tools for running SQL queries against blockchain data:

`query_sql()`

Run a SQL query against downloaded blockchain data.

Parameters:

query (str): SQL query to execute

files (list, optional): List of parquet file paths to query. If None, will use all files in the data directory.

include_schema (bool, optional): Whether to include schema information in the result

Example:

`query_blockchain_sql()`

Query blockchain data using SQL, automatically downloading any required data.

Parameters:

sql_query (str): SQL query to execute

dataset (str, optional): The dataset to query (e.g., 'blocks', 'transactions')

blocks (str, optional): Block range specification

start_block (int, optional): Start block number

end_block (int, optional): End block number

use_latest (bool, optional): If True, query the latest block

blocks_from_latest (int, optional): Number of blocks before the latest to include

contract (str, optional): Contract address to filter by

force_refresh (bool, optional): Force download of new data even if it exists

include_schema (bool, optional): Include schema information in the result

Example:

`list_available_sql_tables()`

List all available tables that can be queried with SQL.

Example:

`get_sql_table_schema()`

Get the schema for a specific parquet file.

Parameters:

file_path (str): Path to the parquet file

Example:

`get_sql_examples()`

Get example SQL queries for different blockchain datasets.

Example:

Configuration Options

When starting the Cryo MCP server, you can use these command-line options:

--rpc-url URL: Ethereum RPC URL (overrides ETH_RPC_URL environment variable)

--data-dir PATH: Directory to store downloaded data (overrides CRYO_DATA_DIR environment variable, defaults to ~/.cryo-mcp/data/)

Environment Variables

ETH_RPC_URL: Default Ethereum RPC URL to use when not specified via command line

CRYO_DATA_DIR: Default directory to store downloaded data when not specified via command line

Advanced Usage

SQL Queries Against Blockchain Data

Cryo MCP allows you to run powerful SQL queries against blockchain data, combining the flexibility of SQL with Cryo's data extraction capabilities:

Two-Step SQL Query Flow

You can split data extraction and querying into two separate steps:

Combined SQL Query Flow

For convenience, you can also use the combined function that handles both steps:

Note: For SQL queries, always use output_format="parquet" when downloading data to ensure optimal performance with DuckDB. When using query_blockchain_sql, you should refer to the file paths directly in your SQL using the read_parquet() function.

Querying with Block Ranges

Cryo MCP supports the full range of Cryo's block specification syntax:

Contract Filtering

Filter logs and other data by contract address:

Column Selection

Include only the columns you need:

Development

Project Structure

Run Tests

uv run pytest

License

MIT

Credits

Built on top of the amazing Cryo tool by Paradigm

Uses the MCP protocol for API communication

Cryo MCP

A Model Completion Protocol (MCP) server for the Cryo blockchain data extraction tool.

For LLM Users: SQL Query Workflow Guide

When using this MCP server to run SQL queries on blockchain data, follow this workflow:

Download data with query_dataset:

Explore schema with get_sql_table_schema:

Run SQL with query_sql:

Alternatively, use the combined approach with query_blockchain_sql:

For a complete working example, see examples/sql_workflow_example.py.

Features

Full Cryo Dataset Access: Query any Cryo dataset through an API server

MCP Integration: Works seamlessly with MCP clients

Flexible Query Options: Support for all major Cryo filtering and output options

Block Range Options: Query specific blocks, latest block, or relative ranges

Contract Filtering: Filter data by contract address

Latest Block Access: Easy access to the latest Ethereum block data

Multiple Output Formats: JSON, CSV, and Parquet support

Schema Information: Get detailed dataset schemas and sample data

SQL Queries: Run SQL queries directly against downloaded blockchain data

Installation (Optional)

This is not required if you will run the tool with uvx directly.

Requirements

Python 3.8+

A working installation of Cryo

Access to an Ethereum RPC endpoint

DuckDB (for SQL query functionality)

Quick Start

Usage with Claude Code

Run claude mcp add for an interactive prompt.

Enter uvx as the command to run.

Enter cryo-mcp --rpc-url <ETH_RPC_URL> [--data-dir <DATA_DIR>] as the args

Alternatively, provide ETH_RPC_URL and CRYO_DATA_DIR as environment variables instead.

New instances of claude will now have access to cryo as configured to hit your RPC endpoint and store data in the specified directory.

Available Tools

Cryo MCP exposes the following MCP tools:

`list_datasets()`

Returns a list of all available Cryo datasets.

Example:

`query_dataset()`

Query a Cryo dataset with various filtering options.

Parameters:

dataset (str): The name of the dataset to query (e.g., 'blocks', 'transactions', 'logs')

blocks (str, optional): Block range specification (e.g., '1000:1010')

start_block (int, optional): Start block number (alternative to blocks)

end_block (int, optional): End block number (alternative to blocks)

use_latest (bool, optional): If True, query the latest block

blocks_from_latest (int, optional): Number of blocks from latest to include

contract (str, optional): Contract address to filter by

output_format (str, optional): Output format ('json', 'csv', 'parquet')

include_columns (list, optional): Columns to include alongside defaults

exclude_columns (list, optional): Columns to exclude from defaults

Example:

`lookup_dataset()`

Get detailed information about a specific dataset, including schema and sample data.

Parameters:

name (str): The name of the dataset to look up

sample_start_block (int, optional): Start block for sample data

sample_end_block (int, optional): End block for sample data

use_latest_sample (bool, optional): Use latest block for sample

sample_blocks_from_latest (int, optional): Number of blocks from latest for sample

Example:

`get_latest_ethereum_block()`

Returns information about the latest Ethereum block.

Example:

SQL Query Tools

Cryo MCP includes several tools for running SQL queries against blockchain data:

`query_sql()`

Run a SQL query against downloaded blockchain data.

Parameters:

query (str): SQL query to execute

files (list, optional): List of parquet file paths to query. If None, will use all files in the data directory.

include_schema (bool, optional): Whether to include schema information in the result

Example:

`query_blockchain_sql()`

Query blockchain data using SQL, automatically downloading any required data.

Parameters:

sql_query (str): SQL query to execute

dataset (str, optional): The dataset to query (e.g., 'blocks', 'transactions')

blocks (str, optional): Block range specification

start_block (int, optional): Start block number

end_block (int, optional): End block number

use_latest (bool, optional): If True, query the latest block

blocks_from_latest (int, optional): Number of blocks before the latest to include

contract (str, optional): Contract address to filter by

force_refresh (bool, optional): Force download of new data even if it exists

include_schema (bool, optional): Include schema information in the result

Example:

`list_available_sql_tables()`

List all available tables that can be queried with SQL.

Example:

`get_sql_table_schema()`

Get the schema for a specific parquet file.

Parameters:

file_path (str): Path to the parquet file

Example:

`get_sql_examples()`

Get example SQL queries for different blockchain datasets.

Example:

Configuration Options

When starting the Cryo MCP server, you can use these command-line options:

--rpc-url URL: Ethereum RPC URL (overrides ETH_RPC_URL environment variable)

--data-dir PATH: Directory to store downloaded data (overrides CRYO_DATA_DIR environment variable, defaults to ~/.cryo-mcp/data/)

Environment Variables

ETH_RPC_URL: Default Ethereum RPC URL to use when not specified via command line

CRYO_DATA_DIR: Default directory to store downloaded data when not specified via command line

Advanced Usage

SQL Queries Against Blockchain Data

Cryo MCP allows you to run powerful SQL queries against blockchain data, combining the flexibility of SQL with Cryo's data extraction capabilities:

Two-Step SQL Query Flow

You can split data extraction and querying into two separate steps:

Combined SQL Query Flow

For convenience, you can also use the combined function that handles both steps:

Querying with Block Ranges

Cryo MCP supports the full range of Cryo's block specification syntax:

Contract Filtering

Filter logs and other data by contract address:

Column Selection

Include only the columns you need:

Development

Project Structure

Run Tests

uv run pytest

License

MIT

Credits

Built on top of the amazing Cryo tool by Paradigm

Uses the MCP protocol for API communication

Cryo MCP

For LLM Users: SQL Query Workflow Guide

Features

Installation (Optional)

Requirements

Quick Start

Usage with Claude Code

Available Tools

`list_datasets()`

`query_dataset()`

`lookup_dataset()`

`get_latest_ethereum_block()`

SQL Query Tools

`query_sql()`

`query_blockchain_sql()`

`list_available_sql_tables()`

`get_sql_table_schema()`

`get_sql_examples()`

Configuration Options

Environment Variables

Advanced Usage

SQL Queries Against Blockchain Data

Two-Step SQL Query Flow

Combined SQL Query Flow

Querying with Block Ranges

Contract Filtering

Column Selection

Development

Project Structure

Run Tests

License

Credits

Cryo MCP

For LLM Users: SQL Query Workflow Guide

Features

Installation (Optional)

Requirements

Quick Start

Usage with Claude Code

Available Tools

`list_datasets()`

`query_dataset()`

`lookup_dataset()`

`get_latest_ethereum_block()`

SQL Query Tools

`query_sql()`

`query_blockchain_sql()`

`list_available_sql_tables()`

`get_sql_table_schema()`

`get_sql_examples()`

Configuration Options

Environment Variables

Advanced Usage

SQL Queries Against Blockchain Data

Two-Step SQL Query Flow

Combined SQL Query Flow

Querying with Block Ranges

Contract Filtering

Column Selection

Development

Project Structure

Run Tests

License

Credits

Related servers

MagicSlides MCP Server

Zerodha MCP Integration

Stock Info (AKShare)

QuickBooks Time