Fix n8n tool call bug: Add **kwargs support to search.py, datasources.py, and chat.py functions for enhanced flexibility.

Author: rodion-m

CLAUDE.md

@@ -41,6 +41,47 @@ docker build -t codealive-mcp .
 docker run --rm -i -e CODEALIVE_API_KEY=your_key_here codealive-mcp
 ```
 
+### Testing
+
+#### Quick Smoke Test
+After making local changes, quickly verify everything works:
+```bash
+# Using make (recommended)
+make smoke-test
+
+# Or directly
+python smoke_test.py
+
+# With valid API key for full testing
+CODEALIVE_API_KEY=your_key python smoke_test.py
+```
+
+The smoke test:
+- ✓ Verifies server starts and connects via stdio
+- ✓ Checks all tools are registered correctly
+- ✓ Tests each tool responds appropriately
+- ✓ Validates parameter handling
+- ✓ Runs in ~5 seconds
+
+#### Unit Tests
+Run comprehensive unit tests with pytest:
+```bash
+# Using make
+make unit-test
+
+# Or directly
+pytest src/tests/ -v
+
+# With coverage
+pytest src/tests/ -v --cov=src
+```
+
+#### All Tests
+Run both smoke tests and unit tests:
+```bash
+make test
+```
+
 ## Architecture
 
 This is a Model Context Protocol (MCP) server that provides AI clients with access to CodeAlive's semantic code search and analysis capabilities.
@@ -59,6 +100,7 @@ This is a Model Context Protocol (MCP) server that provides AI clients with acce
 3. **Streaming Support**: Implements streaming chat completions with proper chunk parsing
 4. **Environment Configuration**: Supports both .env files and command-line arguments with precedence
 5. **Error Handling**: Comprehensive HTTP status code handling with user-friendly error messages
+6. **N8N Middleware**: Strips extra parameters (sessionId, action, chatInput, toolCallId) from n8n tool calls before validation
 
 ### Data Flow
 
@@ -87,9 +129,12 @@ The server is designed to integrate with:
 - Cursor (via MCP settings panel)
 - VS Code with GitHub Copilot (via settings.json)
 - Continue (via config.yaml)
+- n8n (via AI Agent node with MCP tools)
 - Any MCP-compatible AI client
 
-Key integration consideration: AI clients should use `get_data_sources` first to discover available repositories/workspaces, then use those IDs for targeted search and chat operations.
+Key integration considerations:
+- AI clients should use `get_data_sources` first to discover available repositories/workspaces, then use those IDs for targeted search and chat operations
+- **n8n Integration**: The server includes middleware to automatically strip n8n's extra parameters (sessionId, action, chatInput, toolCallId) from tool calls, so n8n works out of the box without any special configuration
 
 ## Publishing and Releases
 

Makefile

@@ -0,0 +1,34 @@
+.PHONY: help install test smoke-test unit-test clean run dev
+
+help:  ## Show this help message
+	@echo "Available commands:"
+	@grep -E '^[a-zA-Z_-]+:.*?## .*$$' $(MAKEFILE_LIST) | awk 'BEGIN {FS = ":.*?## "}; {printf "  \033[36m%-15s\033[0m %s\n", $$1, $$2}'
+
+install:  ## Install dependencies
+	uv pip install -e ".[test]"
+
+smoke-test:  ## Run smoke tests (quick sanity check)
+	@echo "Running smoke tests..."
+	python smoke_test.py
+
+unit-test:  ## Run unit tests with pytest
+	@echo "Running unit tests..."
+	pytest src/tests/ -v
+
+test: unit-test smoke-test  ## Run all tests (unit + smoke)
+
+clean:  ## Clean up cache and temp files
+	rm -rf __pycache__
+	rm -rf .pytest_cache
+	rm -rf src/__pycache__
+	rm -rf src/tests/__pycache__
+	rm -rf *.pyc
+	rm -rf src/*.pyc
+	rm -rf .coverage
+	rm -rf htmlcov
+
+run:  ## Run the MCP server with stdio transport
+	python src/codealive_mcp_server.py
+
+dev:  ## Run the MCP server in debug mode
+	python src/codealive_mcp_server.py --debug

README.md

@@ -6,7 +6,7 @@
 
 **Connect your AI assistant to CodeAlive's powerful code understanding platform in seconds!**
 
-This MCP (Model Context Protocol) server enables AI clients like Claude Code, Cursor, Claude Desktop, Continue, VS Code (GitHub Copilot), Cline, Codex, OpenCode, Qwen Code, Gemini CLI, Roo Code, Goose, Kilo Code, Windsurf, Kiro, Qoder, and Amazon Q Developer to access CodeAlive's advanced semantic code search and codebase interaction features.
+This MCP (Model Context Protocol) server enables AI clients like Claude Code, Cursor, Claude Desktop, Continue, VS Code (GitHub Copilot), Cline, Codex, OpenCode, Qwen Code, Gemini CLI, Roo Code, Goose, Kilo Code, Windsurf, Kiro, Qoder, n8n, and Amazon Q Developer to access CodeAlive's advanced semantic code search and codebase interaction features.
 
 ## What is CodeAlive?
 
@@ -749,6 +749,33 @@ See [JetBrains MCP Documentation](https://www.jetbrains.com/help/ai-assistant/mc
 
 </details>
 
+<details>
+<summary><b>n8n</b></summary>
+
+**Using AI Agent Node with MCP Tools**
+
+1. Add an **AI Agent** node to your workflow
+2. Configure the agent with MCP tools:
+   ```
+   Server URL: https://mcp.codealive.ai/api
+   Authorization Header: Bearer YOUR_API_KEY_HERE
+   ```
+
+3. The server automatically handles n8n's extra parameters (sessionId, action, chatInput, toolCallId)
+4. Use the three available tools:
+   - `get_data_sources` - List available repositories
+   - `codebase_search` - Search code semantically
+   - `codebase_consultant` - Ask questions about code
+
+**Example Workflow:**
+```
+Trigger → AI Agent (with CodeAlive MCP tools) → Process Response
+```
+
+**Note:** n8n middleware is built-in, so no special configuration is needed. The server will automatically strip n8n's extra parameters before processing tool calls.
+
+</details>
+
 ---
 
 ## 🔧 Advanced: Local Development
@@ -810,6 +837,34 @@ python src/codealive_mcp_server.py --transport http --host localhost --port 8000
 curl http://localhost:8000/health
 ```
 
+### Testing Your Local Installation
+
+After making changes, quickly verify everything works:
+
+```bash
+# Quick smoke test (recommended)
+make smoke-test
+
+# Or run directly
+python smoke_test.py
+
+# With your API key for full testing
+CODEALIVE_API_KEY=your_key python smoke_test.py
+
+# Run unit tests
+make unit-test
+
+# Run all tests
+make test
+```
+
+The smoke test verifies:
+- Server starts and connects correctly
+- All tools are registered
+- Each tool responds appropriately
+- Parameter validation works
+- Runs in ~5 seconds
+
 ### Smithery Installation
 
 Auto-install for Claude Desktop via [Smithery](https://smithery.ai/server/@CodeAlive-AI/codealive-mcp):

pyproject.toml

@@ -5,17 +5,18 @@ description = "MCP server for the CodeAlive API"
 readme = "README.md"
 requires-python = ">=3.11"
 dependencies = [
-    "fastmcp==2.12.3",
+    "fastmcp==2.13.0.2",
     "httpx==0.28.1",
     "python-dotenv==1.1.1",
 ]
 
 [project.optional-dependencies]
 test = [
-    "pytest==8.3.6",
-    "pytest-asyncio==0.25.2",
-    "pytest-mock==3.15.0",
-    "pytest-cov==6.0.0",
+    "pytest>=8.0.0,<9.0.0",
+    "pytest-asyncio>=0.23.0,<1.0.0",
+    "pytest-mock>=3.14.0,<4.0.0",
+    "pytest-cov>=4.0.0,<6.0.0",
+    "mcp>=1.0.0",
 ]
 
 [project.scripts]