
Foundry MCP Project
A Model Context Protocol server that enables interaction with Foundry tools through natural language, allowing users to create projects, build contracts, run tests, and manage Ethereum development environments.
README
🧠 Foundry MCP Project
This project is a Model Context Protocol (MCP) server designed to interact with Foundry tools. It provides a set of tools and utilities to manage Foundry projects, run tests, build contracts, and more.
📂 Project Structure
pyproject.toml # Project configuration file
README.md # Project documentation
uv.lock # Dependency lock file
LLM/ # Documentation and SDK usage
src/eth_wh_mcp/ # Source code for the MCP server
🚀 Features
- Create Foundry Projects: Initialize new Foundry projects.
- Build Contracts: Compile Solidity contracts with various options.
- Run Tests: Execute tests with detailed configuration.
- Inspect Contracts: Retrieve ABI, bytecode, and other metadata.
- Run Scripts: Execute Solidity scripts.
- Start Local Nodes: Launch Anvil or Chisel for local Ethereum development.
- Advanced Cast Commands: Execute Ethereum-related commands using
cast
.
🛠️ Installation
-
Clone the repository:
git clone <repository-url>
-
Ensure Foundry tools (
forge
,cast
,anvil
, etc.) are installed and available in your PATH.
🏗️ Usage
Running the MCP Server
To start the MCP server:
python src/eth_wh_mcp/main.py
Available Tools
The following tools are available in the MCP server:
- create_project: Initialize a new Foundry project.
- build_project: Build the current Foundry project.
- test_project: Run tests in the Foundry project.
- clone_contract: Clone a contract from Etherscan.
- run_script: Execute a Solidity script.
- run_cast_command: Run a
cast
command. - start_anvil_with_options: Start the Anvil local Ethereum node.
- start_chisel_with_options: Start the Chisel Solidity REPL.
- inspect_contract: Inspect contract metadata.
- snapshot_project: Create a gas usage snapshot.
- coverage_project: Display test coverage.
📖 Documentation
MCP Python SDK
Refer to the LLM/python-mcp-sdk.md file for detailed usage of the MCP Python SDK, including server construction, tools, prompts, and context handling.
🧪 Development
Local Debugging
Run the MCP server in development mode:
mcp dev src/eth_wh_mcp/main.py --with-editable .
Runtime Execution
To execute the server:
python src/eth_wh_mcp/main.py
📜 License
This project is licensed under the MIT License. See the LICENSE file for details.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.