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

WIP - OpenRouter support

Browse Source
This commit is contained in:
Fahad
2025-06-12 22:45:16 +04:00
parent 52b45f2b03
commit 93daa2942a
6 changed files with 152 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
.env.example
View File

@@ -2,18 +2,25 @@
# Copy this file to .env and fill in your values
# API Keys - At least one is required
#
# IMPORTANT: Use EITHER OpenRouter OR native APIs (Gemini/OpenAI), not both!
# Having both creates ambiguity about which provider serves each model.
#
# Option 1: Use native APIs (recommended for direct access)
# Get your Gemini API key from: https://makersuite.google.com/app/apikey
GEMINI_API_KEY=your_gemini_api_key_here
# Get your OpenAI API key from: https://platform.openai.com/api-keys
OPENAI_API_KEY=your_openai_api_key_here
# Optional: OpenRouter for access to multiple models
# Option 2: Use OpenRouter for access to multiple models through one API
# Get your OpenRouter API key from: https://openrouter.ai/
# If using OpenRouter, comment out the native API keys above
OPENROUTER_API_KEY=your_openrouter_api_key_here
# Optional: Restrict which models can be used via OpenRouter (recommended for cost control)
# Example: OPENROUTER_ALLOWED_MODELS=gpt-4,claude-3-opus,mistral-large
# Leave empty to allow ANY model (not recommended - risk of high costs)
OPENROUTER_ALLOWED_MODELS=
# Optional: Default model to use

10
README.md
View File

@@ -98,9 +98,19 @@ The final implementation resulted in a 26% improvement in JSON parsing performan
- **Windows users**: WSL2 is required for Claude Code CLI
### 1. Get API Keys (at least one required)
**Important:** Choose EITHER native APIs OR OpenRouter, not both:
**Option A: Native APIs (Recommended)**
- **Gemini**: Visit [Google AI Studio](https://makersuite.google.com/app/apikey) and generate an API key. For best results with Gemini 2.5 Pro, use a paid API key as the free tier has limited access to the latest models.
- **OpenAI**: Visit [OpenAI Platform](https://platform.openai.com/api-keys) to get an API key for O3 model access.
**Option B: OpenRouter (Access multiple models with one API)**
- **OpenRouter**: Visit [OpenRouter](https://openrouter.ai/) for access to multiple models through one API. [Setup Guide](docs/openrouter.md)
- Set `OPENROUTER_ALLOWED_MODELS` to restrict which models can be used (recommended)
- Leave empty to allow ANY model (warning: some models are expensive!)
> **Note:** Using both OpenRouter and native APIs creates ambiguity about which provider serves each model. If both are configured, native APIs will take priority.
### 2. Clone and Set Up

42
docs/openrouter.md
View File

@@ -2,6 +2,20 @@
OpenRouter provides unified access to multiple AI models (GPT-4, Claude, Mistral, etc.) through a single API.
## When to Use OpenRouter
**Use OpenRouter when you want:**
- Access to models not available through native APIs (GPT-4, Claude, Mistral, etc.)
- Simplified billing across multiple model providers
- Experimentation with various models without separate API keys
**Use native APIs (Gemini/OpenAI) when you want:**
- Direct access to specific providers without intermediary
- Potentially lower latency and costs
- Access to the latest model features immediately upon release
**Important:** Don't use both OpenRouter and native APIs simultaneously - this creates ambiguity about which provider serves each model.
## Quick Start
### 1. Get API Key
@@ -13,25 +27,33 @@ OpenRouter provides unified access to multiple AI models (GPT-4, Claude, Mistral
```bash
# Add to your .env file
OPENROUTER_API_KEY=your-openrouter-api-key
# IMPORTANT: Set allowed models to control costs
OPENROUTER_ALLOWED_MODELS=gpt-4,claude-3-sonnet,mistral-large
# Or leave empty to allow ANY model (WARNING: risk of high costs!)
# OPENROUTER_ALLOWED_MODELS=
```
That's it! Docker Compose already includes all necessary configuration.
### 3. Use Any Model
### 3. Use Models
**If you set OPENROUTER_ALLOWED_MODELS:**
```
# Examples
# Only these models will work:
"Use gpt-4 via zen to review this code"
"Use claude-3-opus via zen to debug this error"
"Use claude-3-sonnet via zen to debug this error"
"Use mistral-large via zen to optimize this algorithm"
```
## Cost Control (Recommended)
Restrict which models can be used to prevent unexpected charges:
```bash
# Add to .env file - only allow specific models
OPENROUTER_ALLOWED_MODELS=gpt-4,claude-3-sonnet,mistral-large
**If you leave OPENROUTER_ALLOWED_MODELS empty:**
```
# ANY model available on OpenRouter will work:
"Use gpt-4o via zen to analyze this"
"Use claude-3-opus via zen for deep analysis"
"Use deepseek-coder via zen to generate code"
# WARNING: Some models can be very expensive!
```
Check current model pricing at [openrouter.ai/models](https://openrouter.ai/models).

62
server.py
View File

@@ -125,7 +125,7 @@ def configure_providers():
At least one valid API key (Gemini or OpenAI) is required.
Raises:
ValueError: If no valid API keys are found
ValueError: If no valid API keys are found or conflicting configurations detected
"""
from providers import ModelProviderRegistry
from providers.base import ProviderType
@@ -134,28 +134,59 @@ def configure_providers():
from providers.openrouter import OpenRouterProvider
valid_providers = []
has_native_apis = False
has_openrouter = False
# Check for Gemini API key
gemini_key = os.getenv("GEMINI_API_KEY")
if gemini_key and gemini_key != "your_gemini_api_key_here":
ModelProviderRegistry.register_provider(ProviderType.GOOGLE, GeminiModelProvider)
valid_providers.append("Gemini")
has_native_apis = True
logger.info("Gemini API key found - Gemini models available")
# Check for OpenAI API key
openai_key = os.getenv("OPENAI_API_KEY")
if openai_key and openai_key != "your_openai_api_key_here":
ModelProviderRegistry.register_provider(ProviderType.OPENAI, OpenAIModelProvider)
valid_providers.append("OpenAI (o3)")
has_native_apis = True
logger.info("OpenAI API key found - o3 model available")
# Check for OpenRouter API key
openrouter_key = os.getenv("OPENROUTER_API_KEY")
if openrouter_key and openrouter_key != "your_openrouter_api_key_here":
ModelProviderRegistry.register_provider(ProviderType.OPENROUTER, OpenRouterProvider)
valid_providers.append("OpenRouter")
has_openrouter = True
logger.info("OpenRouter API key found - Multiple models available via OpenRouter")
# Check for conflicting configuration
if has_native_apis and has_openrouter:
logger.warning(
"\n" + "=" * 70 + "\n"
"WARNING: Both OpenRouter and native API keys detected!\n"
"\n"
"This creates ambiguity about which provider will be used for models\n"
"available through both APIs (e.g., 'o3' could come from OpenAI or OpenRouter).\n"
"\n"
"RECOMMENDATION: Use EITHER OpenRouter OR native APIs, not both.\n"
"\n"
"To fix this:\n"
"1. Use only OpenRouter: unset GEMINI_API_KEY and OPENAI_API_KEY\n"
"2. Use only native APIs: unset OPENROUTER_API_KEY\n"
"\n"
"Current configuration will prioritize native APIs over OpenRouter.\n" +
"=" * 70 + "\n"
)
# Register providers - native APIs first to ensure they take priority
if has_native_apis:
if gemini_key and gemini_key != "your_gemini_api_key_here":
ModelProviderRegistry.register_provider(ProviderType.GOOGLE, GeminiModelProvider)
if openai_key and openai_key != "your_openai_api_key_here":
ModelProviderRegistry.register_provider(ProviderType.OPENAI, OpenAIModelProvider)
# Register OpenRouter last so native APIs take precedence
if has_openrouter:
ModelProviderRegistry.register_provider(ProviderType.OPENROUTER, OpenRouterProvider)
# Require at least one valid provider
if not valid_providers:
@@ -168,6 +199,10 @@ def configure_providers():
logger.info(f"Available providers: {', '.join(valid_providers)}")
# Log provider priority if both are configured
if has_native_apis and has_openrouter:
logger.info("Provider priority: Native APIs (Gemini, OpenAI) will be checked before OpenRouter")
@server.list_tools()
async def handle_list_tools() -> list[Tool]:
@@ -504,6 +539,22 @@ async def handle_get_version() -> list[TextContent]:
"available_tools": list(TOOLS.keys()) + ["get_version"],
}
# Check configured providers
from providers import ModelProviderRegistry
from providers.base import ProviderType
configured_providers = []
if ModelProviderRegistry.get_provider(ProviderType.GOOGLE):
configured_providers.append("Gemini (flash, pro)")
if ModelProviderRegistry.get_provider(ProviderType.OPENAI):
configured_providers.append("OpenAI (o3, o3-mini)")
if ModelProviderRegistry.get_provider(ProviderType.OPENROUTER):
openrouter_allowed = os.getenv("OPENROUTER_ALLOWED_MODELS", "")
if openrouter_allowed:
configured_providers.append(f"OpenRouter (restricted to: {openrouter_allowed})")
else:
configured_providers.append("OpenRouter (ANY model on openrouter.ai)")
# Format the information in a human-readable way
text = f"""Zen MCP Server v{__version__}
Updated: {__updated__}
@@ -516,6 +567,9 @@ Configuration:
- Python: {version_info["python_version"]}
- Started: {version_info["server_started"]}
Configured Providers:
{chr(10).join(f" - {provider}" for provider in configured_providers)}
Available Tools:
{chr(10).join(f" - {tool}" for tool in version_info["available_tools"])}

29
setup-docker.sh
View File

@@ -118,6 +118,35 @@ if [ -n "${OPENROUTER_API_KEY:-}" ] && [ "$OPENROUTER_API_KEY" != "your_openrout
echo "✅ Valid OPENROUTER_API_KEY found"
fi
# Check for conflicting configuration
if [ "$VALID_OPENROUTER_KEY" = true ] && ([ "$VALID_GEMINI_KEY" = true ] || [ "$VALID_OPENAI_KEY" = true ]); then
echo ""
echo "⚠️ WARNING: Conflicting API configuration detected!"
echo ""
echo "You have configured both:"
echo " - OpenRouter API key"
if [ "$VALID_GEMINI_KEY" = true ]; then
echo " - Native Gemini API key"
fi
if [ "$VALID_OPENAI_KEY" = true ]; then
echo " - Native OpenAI API key"
fi
echo ""
echo "This creates ambiguity about which provider to use for models available"
echo "through multiple APIs (e.g., 'o3' could come from OpenAI or OpenRouter)."
echo ""
echo "RECOMMENDATION: Use EITHER OpenRouter OR native APIs, not both."
echo ""
echo "To fix this, edit .env and:"
echo " Option 1: Use only OpenRouter - comment out GEMINI_API_KEY and OPENAI_API_KEY"
echo " Option 2: Use only native APIs - comment out OPENROUTER_API_KEY"
echo ""
echo "The server will start anyway, but native APIs will take priority over OpenRouter."
echo ""
# Give user time to read the warning
sleep 3
fi
# Require at least one valid API key
if [ "$VALID_GEMINI_KEY" = false ] && [ "$VALID_OPENAI_KEY" = false ] && [ "$VALID_OPENROUTER_KEY" = false ]; then
echo ""

16
tools/base.py
View File

@@ -153,12 +153,20 @@ class BaseTool(ABC):
Dict containing the model field JSON schema
"""
from config import DEFAULT_MODEL, IS_AUTO_MODE, MODEL_CAPABILITIES_DESC
import os
# Check if OpenRouter is configured
has_openrouter = bool(os.getenv("OPENROUTER_API_KEY") and
os.getenv("OPENROUTER_API_KEY") != "your_openrouter_api_key_here")
if IS_AUTO_MODE:
# In auto mode, model is required and we provide detailed descriptions
model_desc_parts = ["Choose the best model for this task based on these capabilities:"]
for model, desc in MODEL_CAPABILITIES_DESC.items():
model_desc_parts.append(f"- '{model}': {desc}")
if has_openrouter:
model_desc_parts.append("\nOpenRouter models: If configured, you can also use ANY model available on OpenRouter (e.g., 'gpt-4', 'claude-3-opus', 'mistral-large'). Check openrouter.ai/models for available models.")
return {
"type": "string",
@@ -169,9 +177,15 @@ class BaseTool(ABC):
# Normal mode - model is optional with default
available_models = list(MODEL_CAPABILITIES_DESC.keys())
models_str = ", ".join(f"'{m}'" for m in available_models)
description = f"Model to use. Native models: {models_str}."
if has_openrouter:
description += " OpenRouter: Any model available on openrouter.ai (e.g., 'gpt-4', 'claude-3-opus', 'mistral-large')."
description += f" Defaults to '{DEFAULT_MODEL}' if not specified."
return {
"type": "string",
"description": f"Model to use. Available: {models_str}. Defaults to '{DEFAULT_MODEL}' if not specified.",
"description": description,
}
def get_default_temperature(self) -> float: