MCP server for querying Ethereum blockchain data using cryo
Project description
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.
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 and CSV support
- Schema Information: Get detailed dataset schemas and sample data
Installation (Optional)
This is not required if you will run the tool with uvx directly.
# install with UV (recommended)
uv tool install cryo-mcp
Requirements
- Python 3.8+
- uv
- A working installation of Cryo
- Access to an Ethereum RPC endpoint
Quick Start
Usage with Claude Code
- Run
claude mcp addfor an interactive prompt. - Enter
uvxas the command to run. - Enter
cryo-mcp -r <ETH_RPC_URL>as the args - Alternatively, provide
ETH_RPC_URLas an environment variable instead.
New instances of claude will now have access to cryo as configured to hit your RPC endpoint.
Available Tools
Cryo MCP exposes the following MCP tools:
list_datasets()
Returns a list of all available Cryo datasets.
Example:
client.list_datasets()
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 blockblocks_from_latest(int, optional): Number of blocks from latest to includecontract(str, optional): Contract address to filter byoutput_format(str, optional): Output format ('json', 'csv')include_columns(list, optional): Columns to include alongside defaultsexclude_columns(list, optional): Columns to exclude from defaults
Example:
# Get transactions from blocks 15M to 15.01M
client.query_dataset('transactions', blocks='15M:15.01M')
# Get logs for a specific contract from the latest 100 blocks
client.query_dataset('logs', blocks_from_latest=100, contract='0x1234...')
# Get just the latest block
client.query_dataset('blocks', use_latest=True)
lookup_dataset()
Get detailed information about a specific dataset, including schema and sample data.
Parameters:
name(str): The name of the dataset to look upsample_start_block(int, optional): Start block for sample datasample_end_block(int, optional): End block for sample datause_latest_sample(bool, optional): Use latest block for samplesample_blocks_from_latest(int, optional): Number of blocks from latest for sample
Example:
client.lookup_dataset('logs')
get_latest_ethereum_block()
Returns information about the latest Ethereum block.
Example:
client.get_latest_ethereum_block()
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)
Environment Variables
ETH_RPC_URL: Default Ethereum RPC URL to use when not specified via command line
Advanced Usage
Querying with Block Ranges
Cryo MCP supports the full range of Cryo's block specification syntax:
# Using block numbers
client.query_dataset('transactions', blocks='15000000:15001000')
# Using K/M notation
client.query_dataset('logs', blocks='15M:15.01M')
# Using offsets from latest
client.query_dataset('blocks', blocks_from_latest=100)
Contract Filtering
Filter logs and other data by contract address:
# Get all logs for USDC contract
client.query_dataset('logs',
blocks='16M:16.1M',
contract='0xa0b86991c6218b36c1d19d4a2e9eb0ce3606eb48')
Column Selection
Include only the columns you need:
# Get just block numbers and timestamps
client.query_dataset('blocks',
blocks='16M:16.1M',
include_columns=['number', 'timestamp'])
Development
Project Structure
cryo-mcp/
├── cryo_mcp/ # Main package directory
│ ├── __init__.py # Package initialization
│ ├── server.py # Main MCP server implementation
├── tests/ # Test directory
│ ├── test_*.py # Test files
├── pyproject.toml # Project configuration
├── README.md # Project documentation
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
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file cryo_mcp-0.1.0.tar.gz.
File metadata
- Download URL: cryo_mcp-0.1.0.tar.gz
- Upload date:
- Size: 66.3 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.5.8
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
4fa49c8c1765ff030f7f79d8df00bb06b9ba74d4251760229bd3cc4d0c51f8b2
|
|
| MD5 |
f4108ff2b4dd58513a018ad9287cf69c
|
|
| BLAKE2b-256 |
be813d488506382550c8b39776f97d4eff37c53441aa6bcf88a4b1bd495de1cd
|
File details
Details for the file cryo_mcp-0.1.0-py3-none-any.whl.
File metadata
- Download URL: cryo_mcp-0.1.0-py3-none-any.whl
- Upload date:
- Size: 9.9 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.5.8
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
bb6e955beefe0867ef37921d145a0ec302e3cebf7c04e692be3f29cd7acecca3
|
|
| MD5 |
635819b0824aba17ee7ee1765fc30716
|
|
| BLAKE2b-256 |
72cd3f3e2f8aaf3d6797c7bcfec15f4b7e27dde4f197c9f11ef66cea0e9fca0e
|