Hanzo MCP is a comprehensive Model Context Protocol server that provides a unified interface for accessing over 65 professional tools in one installation. Unlike other MCP servers that offer fragmented experiences, Hanzo MCP allows you to orchestrate multiple MCP servers through a single, consistent interface with customizable configurations through its palette system.
# Install globally with uvx
uvx hanzo-mcp
# Install with pip
pip install hanzo-mcp
# Install from source
git clone https://github.com/hanzoai/mcp
cd mcp
make install
Note: If you encounter Pydantic deprecation warnings, clear your uvx cache with
rm -rf ~/.cache/uv/
and run again.
make install-desktop
cat >> ~/Library/Application\ Support/Claude/claude_desktop_config.json << 'EOF'
{
"mcpServers": {
"hanzo": {
"command": "uvx",
"args": ["hanzo-mcp"]
}
}
}
EOF
search
to explore any codebasetree
edit
or multi_edit
run_command
mcp_add
Customize Hanzo MCP's behavior and available tools with palettes:
# List available palettes
palette_list()
# Switch to a different palette
palette_load(palette="minimal") # Just core tools
palette_load(palette="academic") # Research and writing focused
palette_load(palette="devops") # Infrastructure and deployment
# Create your own custom palette
palette_create(
name="my-workflow",
tools=["read", "write", "edit", "search", "my-custom-tool"],
config={"editor": "vim", "search_backend": "ripgrep"}
)
Hanzo MCP can orchestrate other MCP servers:
# Add another MCP server
mcp_add(url="github.com/modelcontextprotocol/servers/tree/main/postgres")
# List installed servers
mcp_stats()
# Use tools from other servers
postgres_query(query="SELECT * FROM users")
# Remove an MCP server
mcp_remove(alias="postgres")
# Multi-modal search across your codebase
results = search(
query="authentication",
include_git=True, # Search git history
include_vector=True, # Semantic search
include_ast=True, # AST symbol search
parallel=True # Search all modes concurrently
)
# Delegate complex tasks to specialized agents
agent(
task="Refactor this codebase to use async/await",
files=["src/**/*.py"],
instructions="Maintain backwards compatibility"
)
# Query multiple LLMs and get consensus
llm(
action="consensus",
prompt="Is this code secure?",
providers=["openai", "anthropic", "google"],
threshold=0.8
)
To add this MCP server to Claude Code, run this command in your terminal:
claude mcp add-json "hanzo" '{"command":"uvx","args":["hanzo-mcp"]}'
See the official Claude Code MCP documentation for more details.
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json
file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json
file.
To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".
When you click that button the ~/.cursor/mcp.json
file will be opened and you can add your server like this:
{
"mcpServers": {
"hanzo": {
"command": "uvx",
"args": [
"hanzo-mcp"
]
}
}
}
To add an MCP server to a project you can create a new .cursor/mcp.json
file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.
To add this MCP server to Claude Desktop:
1. Find your configuration file:
~/Library/Application Support/Claude/claude_desktop_config.json
%APPDATA%\Claude\claude_desktop_config.json
~/.config/Claude/claude_desktop_config.json
2. Add this to your configuration file:
{
"mcpServers": {
"hanzo": {
"command": "uvx",
"args": [
"hanzo-mcp"
]
}
}
}
3. Restart Claude Desktop for the changes to take effect