torbjorn/my-pal-mcp-server
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Support for Gemini CLI (setup instructions) - WIP

Browse Source
This commit is contained in:
Fahad
2025-06-25 19:36:09 +04:00
parent 9c1503faac
commit 6d0bafa81d
7 changed files with 276 additions and 83 deletions
Download Patch File Download Diff File Expand all files Collapse all files

86
README.md
View File

@@ -3,12 +3,12 @@
[zen_web.webm](https://github.com/user-attachments/assets/851e3911-7f06-47c0-a4ab-a2601236697c)
<div align="center">
<b>🤖 Claude + [Gemini / OpenAI / Grok / OpenRouter / DIAL / Ollama / Any Model] = Your Ultimate AI Development Team</b>
<b>🤖 [Claude](https://www.anthropic.com/claude-code) OR [Gemini CLI](https://github.com/google-gemini/gemini-cli) + [Gemini / OpenAI / Grok / OpenRouter / DIAL / Ollama / Any Model] = Your Ultimate AI Development Team</b>
</div>
<br/>
The ultimate development partners for Claude - a Model Context Protocol server that gives Claude access to multiple AI
The ultimate development partners for your favorite Coding Agent ([Claude](https://www.anthropic.com/claude-code) OR [Gemini CLI](https://github.com/google-gemini/gemini-cli)) - a Model Context Protocol server that gives you access to multiple AI
models for enhanced code analysis, problem-solving, and collaborative development.
**Features true AI orchestration with conversations that continue across workflows** - Give Claude a complex
@@ -73,7 +73,7 @@ Because these AI models [clearly aren't when they get chatty →](docs/ai_banter
- [Complete Advanced Guide](docs/advanced-usage.md) - Model configuration, thinking modes, workflows, tool parameters
- **Setup & Support**
- [WSL Setup Guide](#21-wsl-windows-subsystem-for-linux-setup-guide) - Windows Subsystem for Linux configuration
- [WSL Setup Guide](docs/wsl-setup.md) - Windows Subsystem for Linux configuration
- [Troubleshooting Guide](docs/troubleshooting.md) - Common issues and debugging steps
- [License](#license) - Apache 2.0
@@ -181,85 +181,13 @@ cd zen-mcp-server
- **Sets up everything automatically** - Python environment, dependencies, configuration
- **Configures Claude integrations** - Adds to Claude Code CLI and guides Desktop setup
- **Ready to use immediately** - No manual configuration needed
- **Also works with Gemini CLI** - See [Gemini CLI Setup](docs/gemini-setup.md) for configuration
**After updates:** Always run `./run-server.sh` again after `git pull` to ensure everything stays current.
**Windows users:** Using WSL? See the [WSL Setup Guide](docs/wsl-setup.md) for detailed instructions.
### 2.1. WSL (Windows Subsystem for Linux) Setup Guide
If you're running on Windows with WSL, follow these additional steps to ensure proper configuration:
#### Prerequisites for WSL
```bash
# Update WSL and ensure you have a recent Ubuntu distribution
sudo apt update && sudo apt upgrade -y
# Install required system dependencies
sudo apt install -y python3-venv python3-pip curl git
# Install Node.js and npm (required for Claude Code CLI)
curl -fsSL https://deb.nodesource.com/setup_lts.x | sudo -E bash -
sudo apt install -y nodejs
# Install Claude Code CLI globally
npm install -g @anthropic-ai/claude-code
```
#### WSL-Specific Installation Steps
1. **Clone the repository in your WSL environment** (not in Windows filesystem):
```bash
# Navigate to your home directory or preferred location in WSL
cd ~
# Clone the repository
git clone https://github.com/BeehiveInnovations/zen-mcp-server.git
cd zen-mcp-server
```
2. **Run the setup script**:
```bash
# Make the script executable and run it
chmod +x run-server.sh
./run-server.sh
```
3. **Verify Claude Code can find the MCP server**:
```bash
# List configured MCP servers
claude mcp list
# You should see 'zen' listed in the output
# If not, the setup script will provide the correct configuration
```
#### Troubleshooting WSL Issues
**Python Environment Issues:**
```bash
# If you encounter Python virtual environment issues
sudo apt install -y python3.12-venv python3.12-dev
# Ensure pip is up to date
python3 -m pip install --upgrade pip
```
**Path Issues:**
- Always use the full WSL path for MCP configuration (e.g., `/home/YourName/zen-mcp-server/`)
- The setup script automatically detects WSL and configures the correct paths
**Claude Code Connection Issues:**
```bash
# If Claude Code can't connect to the MCP server, check the configuration
cat ~/.claude.json | grep -A 10 "zen"
# The configuration should show the correct WSL path to the Python executable
# Example: "/home/YourName/zen-mcp-server/.zen_venv/bin/python"
```
**Performance Tip:** For best performance, keep your zen-mcp-server directory in the WSL filesystem (e.g., `~/zen-mcp-server`) rather than in the Windows filesystem (`/mnt/c/...`).
### 4. Add Your API Keys
### 3. Add Your API Keys
```bash
# Edit .env to add your API keys (if not already set in environment)
@@ -297,7 +225,7 @@ If you were already running a `claude` code session, please exit and start a new
2. **Copy the configuration** shown by `./run-server.sh -c` into your `claude_desktop_config.json`
3. **Restart Claude Desktop** for changes to take effect
### 5. Start Using It!
### 4. Start Using It!
Just ask Claude naturally:
- "Think deeper about this architecture design with zen" → Claude picks best model + `thinkdeep`

43
docs/gemini-setup.md Normal file
View File

@@ -0,0 +1,43 @@
# Gemini CLI Setup
> **Note**: While Zen MCP Server connects successfully to Gemini CLI, tool invocation is not working
> correctly yet. We'll update this guide once the integration is fully functional.
This guide explains how to configure Zen MCP Server to work with [Gemini CLI](https://github.com/google-gemini/gemini-cli).
## Prerequisites
- Zen MCP Server installed and configured
- Gemini CLI installed
- At least one API key configured in your `.env` file
## Configuration
1. Edit `~/.gemini/settings.json` and add:
```json
{
"mcpServers": {
"zen": {
"command": "/path/to/zen-mcp-server/zen-mcp-server"
}
}
}
```
2. Replace `/path/to/zen-mcp-server` with your actual Zen installation path.
3. If the `zen-mcp-server` wrapper script doesn't exist, create it:
```bash
#!/bin/bash
DIR="$(cd "$(dirname "$0")" && pwd)"
cd "$DIR"
exec .zen_venv/bin/python server.py "$@"
```
Then make it executable: `chmod +x zen-mcp-server`
4. Restart Gemini CLI.
All 15 Zen tools are now available in your Gemini CLI session.

79
docs/wsl-setup.md Normal file
View File

@@ -0,0 +1,79 @@
# WSL (Windows Subsystem for Linux) Setup Guide
This guide provides detailed instructions for setting up Zen MCP Server on Windows using WSL.
## Prerequisites for WSL
```bash
# Update WSL and ensure you have a recent Ubuntu distribution
sudo apt update && sudo apt upgrade -y
# Install required system dependencies
sudo apt install -y python3-venv python3-pip curl git
# Install Node.js and npm (required for Claude Code CLI)
curl -fsSL https://deb.nodesource.com/setup_lts.x | sudo -E bash -
sudo apt install -y nodejs
# Install Claude Code CLI globally
npm install -g @anthropic-ai/claude-code
```
## WSL-Specific Installation Steps
1. **Clone the repository in your WSL environment** (not in Windows filesystem):
```bash
# Navigate to your home directory or preferred location in WSL
cd ~
# Clone the repository
git clone https://github.com/BeehiveInnovations/zen-mcp-server.git
cd zen-mcp-server
```
2. **Run the setup script**:
```bash
# Make the script executable and run it
chmod +x run-server.sh
./run-server.sh
```
3. **Verify Claude Code can find the MCP server**:
```bash
# List configured MCP servers
claude mcp list
# You should see 'zen' listed in the output
# If not, the setup script will provide the correct configuration
```
## Troubleshooting WSL Issues
### Python Environment Issues
```bash
# If you encounter Python virtual environment issues
sudo apt install -y python3.12-venv python3.12-dev
# Ensure pip is up to date
python3 -m pip install --upgrade pip
```
### Path Issues
- Always use the full WSL path for MCP configuration (e.g., `/home/YourName/zen-mcp-server/`)
- The setup script automatically detects WSL and configures the correct paths
### Claude Code Connection Issues
```bash
# If Claude Code can't connect to the MCP server, check the configuration
cat ~/.claude.json | grep -A 10 "zen"
# The configuration should show the correct WSL path to the Python executable
# Example: "/home/YourName/zen-mcp-server/.zen_venv/bin/python"
```
### Performance Tip
For best performance, keep your zen-mcp-server directory in the WSL filesystem (e.g., `~/zen-mcp-server`) rather than in the Windows filesystem (`/mnt/c/...`).

118
run-server.sh
View File

@@ -1298,11 +1298,108 @@ EOF
fi
}
# Check and update Gemini CLI configuration
check_gemini_cli_integration() {
local script_dir="$1"
local zen_wrapper="$script_dir/zen-mcp-server"
# Check if Gemini settings file exists
local gemini_config="$HOME/.gemini/settings.json"
if [[ ! -f "$gemini_config" ]]; then
# Gemini CLI not installed or not configured
return 0
fi
# Check if zen is already configured
if grep -q '"zen"' "$gemini_config" 2>/dev/null; then
# Already configured
return 0
fi
# Ask user if they want to add Zen to Gemini CLI
echo ""
read -p "Configure Zen for Gemini CLI? (Y/n): " -n 1 -r
echo ""
if [[ $REPLY =~ ^[Nn]$ ]]; then
print_info "Skipping Gemini CLI integration"
return 0
fi
# Ensure wrapper script exists
if [[ ! -f "$zen_wrapper" ]]; then
print_info "Creating wrapper script for Gemini CLI..."
cat > "$zen_wrapper" << 'EOF'
#!/bin/bash
# Wrapper script for Gemini CLI compatibility
DIR="$(cd "$(dirname "$0")" && pwd)"
cd "$DIR"
exec .zen_venv/bin/python server.py "$@"
EOF
chmod +x "$zen_wrapper"
print_success "Created zen-mcp-server wrapper script"
fi
# Update Gemini settings
print_info "Updating Gemini CLI configuration..."
# Create backup
cp "$gemini_config" "${gemini_config}.backup_$(date +%Y%m%d_%H%M%S)"
# Add zen configuration using Python for proper JSON handling
local temp_file=$(mktemp)
python3 -c "
import json
import sys
try:
with open('$gemini_config', 'r') as f:
config = json.load(f)
# Ensure mcpServers exists
if 'mcpServers' not in config:
config['mcpServers'] = {}
# Add zen server
config['mcpServers']['zen'] = {
'command': '$zen_wrapper'
}
with open('$temp_file', 'w') as f:
json.dump(config, f, indent=2)
except Exception as e:
print(f'Error processing config: {e}', file=sys.stderr)
sys.exit(1)
" && mv "$temp_file" "$gemini_config"
if [[ $? -eq 0 ]]; then
print_success "Successfully configured Gemini CLI"
echo " Config: $gemini_config"
echo " Restart Gemini CLI to use Zen MCP Server"
else
print_error "Failed to update Gemini CLI config"
echo "Manual config location: $gemini_config"
echo "Add this configuration:"
cat << EOF
{
"mcpServers": {
"zen": {
"command": "$zen_wrapper"
}
}
}
EOF
fi
}
# Display configuration instructions
display_config_instructions() {
local python_cmd="$1"
local server_path="$2"
# Get script directory for Gemini CLI config
local script_dir=$(dirname "$server_path")
echo ""
local config_header="ZEN MCP SERVER CONFIGURATION"
echo "===== $config_header ====="
@@ -1340,6 +1437,20 @@ EOF
echo ""
print_info "3. Restart Claude Desktop after updating the config file"
echo ""
print_info "For Gemini CLI:"
echo " Add this configuration to ~/.gemini/settings.json:"
echo ""
cat << EOF
{
"mcpServers": {
"zen": {
"command": "$script_dir/zen-mcp-server"
}
}
}
EOF
echo ""
}
# Display setup instructions
@@ -1509,7 +1620,10 @@ main() {
check_claude_cli_integration "$python_cmd" "$server_path"
check_claude_desktop_integration "$python_cmd" "$server_path"
# Step 10: Display log information
# Step 10: Check Gemini CLI integration
check_gemini_cli_integration "$script_dir"
# Step 11: Display log information
echo ""
echo "Logs will be written to: $script_dir/$LOG_DIR/$LOG_FILE"
echo ""
@@ -1522,7 +1636,7 @@ main() {
echo "To show config: ./run-server.sh -c"
echo "To update: git pull, then run ./run-server.sh again"
echo ""
echo "Happy Clauding! 🎉"
echo "Happy coding! 🎉"
fi
}

11
tools/listmodels.py
View File

@@ -43,7 +43,16 @@ class ListModelsTool(BaseTool):
def get_input_schema(self) -> dict[str, Any]:
"""Return the JSON schema for the tool's input"""
return {"type": "object", "properties": {}, "required": []}
return {
"type": "object",
"properties": {
"model": {
"type": "string",
"description": "Model to use (ignored by listmodels tool)"
}
},
"required": []
}
def get_system_prompt(self) -> str:
"""No AI model needed for this tool"""

11
tools/version.py
View File

@@ -147,7 +147,16 @@ class VersionTool(BaseTool):
def get_input_schema(self) -> dict[str, Any]:
"""Return the JSON schema for the tool's input"""
return {"type": "object", "properties": {}, "required": []}
return {
"type": "object",
"properties": {
"model": {
"type": "string",
"description": "Model to use (ignored by version tool)"
}
},
"required": []
}
def get_system_prompt(self) -> str:
"""No AI model needed for this tool"""

11
zen-mcp-server Executable file
View File

@@ -0,0 +1,11 @@
#!/bin/bash
# Wrapper script for Gemini CLI compatibility
# Get the directory of this script
DIR="$(cd "$(dirname "$0")" && pwd)"
# Change to the zen-mcp-server directory
cd "$DIR"
# Execute the Python server with all arguments passed through
exec .zen_venv/bin/python server.py "$@"