Major refactoring to properly integrate with LiteLLM's Responses API, which handles
MCP tool execution automatically instead of requiring manual tool call loops.
Key changes:
- Switched from chat.completions.create() to client.responses.create()
- Use "server_url": "litellm_proxy" to leverage LiteLLM as MCP gateway
- Set "require_approval": "never" for fully automatic tool execution
- Simplified get_available_mcp_tools() to get_available_mcp_servers()
- Removed manual OpenAI tool format conversion (LiteLLM handles this)
- Updated response extraction to use output[0].content[0].text format
- Convert system prompts to user role for Responses API compatibility
Technical improvements:
- LiteLLM now handles the complete tool calling loop automatically
- No more placeholder responses - actual MCP tools will execute
- Cleaner code with ~100 fewer lines
- Better separation between tools-enabled and tools-disabled paths
- Proper error handling for Responses API format
Responses API benefits:
- Single API call returns final response with tool results integrated
- Automatic tool discovery, execution, and result formatting
- No manual tracking of tool_call_ids or conversation state
- Native MCP support via server_label configuration
Documentation:
- Added comprehensive litellm-mcp-research.md with API examples
- Documented Responses API vs chat.completions differences
- Included Discord bot migration patterns
- Covered authentication, streaming, and tool restrictions
Next steps:
- Test with actual Discord interactions
- Verify GitHub MCP tools execute correctly
- Monitor response extraction for edge cases
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Major improvements to LiteLLM Discord bot with MCP (Model Context Protocol) tools support:
Features added:
- MCP tools discovery and integration with LiteLLM proxy
- Fetch and convert 40+ GitHub MCP tools to OpenAI format
- Tool calling flow with placeholder execution (pending MCP endpoint confirmation)
- Dynamic tool injection based on LiteLLM MCP server configuration
- Enhanced system prompt with tool usage guidance
- Added ENABLE_TOOLS environment variable for easy toggle
- Comprehensive debug logging for troubleshooting
Technical changes:
- Added httpx>=0.25.0 dependency for async MCP API calls
- Implemented get_available_mcp_tools() to query /v1/mcp/server and /v1/mcp/tools endpoints
- Convert MCP tool schemas to OpenAI function calling format
- Detect and handle tool_calls in model responses
- Added system_prompt.txt for customizable bot behavior
- Updated README with better documentation and setup instructions
- Created claude.md with detailed development notes and upgrade roadmap
Configuration:
- New ENABLE_TOOLS flag in .env to control MCP integration
- DEBUG_LOGGING for detailed execution logs
- System prompt file support for easy customization
Known limitations:
- Tool execution currently uses placeholders (MCP execution endpoint needs verification)
- Limited to 50 tools to avoid overwhelming the model
- Requires LiteLLM proxy with MCP server configured
Next steps:
- Verify correct LiteLLM MCP tool execution endpoint
- Implement actual tool execution via MCP proxy
- Test end-to-end GitHub operations through Discord
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
