feat(C2.8): Add scrape_codebase MCP tool for local codebase analysis

- Add scrape_codebase_tool() to scraping_tools.py (67 lines)
- Register tool in MCP server with @safe_tool_decorator
- Add tool to FastMCP server imports and exports
- Add 2 comprehensive tests for basic and advanced usage
- Update MCP server tool count from 17 to 18 tools
- Tool supports directory analysis with configurable depth
- Features: language filtering, file patterns, API reference generation

Closes #70 - C2.8 MCP Tool Integration complete

Related:
- Builds on C2.7 (codebase_scraper.py CLI tool)
- Uses existing code_analyzer.py infrastructure
- Follows same pattern as scrape_github and scrape_pdf tools

Test coverage:
- test_scrape_codebase_basic: Basic codebase analysis
- test_scrape_codebase_with_options: Advanced options testing

src/skill_seekers/mcp/server_fastmcp.py

@@ -3,16 +3,16 @@
 Skill Seeker MCP Server (FastMCP Implementation)
 
 Modern, decorator-based MCP server using FastMCP for simplified tool registration.
-Provides 17 tools for generating Claude AI skills from documentation.
+Provides 18 tools for generating Claude AI skills from documentation.
 
 This is a streamlined alternative to server.py (2200 lines → 708 lines, 68% reduction).
 All tool implementations are delegated to modular tool files in tools/ directory.
 
 **Architecture:**
 - FastMCP server with decorator-based tool registration
-- 17 tools organized into 5 categories:
+- 18 tools organized into 5 categories:
   * Config tools (3): generate_config, list_configs, validate_config
-  * Scraping tools (4): estimate_pages, scrape_docs, scrape_github, scrape_pdf
+  * Scraping tools (5): estimate_pages, scrape_docs, scrape_github, scrape_pdf, scrape_codebase
   * Packaging tools (3): package_skill, upload_skill, install_skill
   * Splitting tools (2): split_config, generate_router
   * Source tools (5): fetch_config, submit_config, add_config_source, list_config_sources, remove_config_source
@@ -81,6 +81,7 @@ try:
         scrape_docs_impl,
         scrape_github_impl,
         scrape_pdf_impl,
+        scrape_codebase_impl,
         # Packaging tools
         package_skill_impl,
         upload_skill_impl,
@@ -108,6 +109,7 @@ except ImportError:
         scrape_docs_impl,
         scrape_github_impl,
         scrape_pdf_impl,
+        scrape_codebase_impl,
         package_skill_impl,
         upload_skill_impl,
         enhance_skill_impl,
@@ -393,6 +395,46 @@ async def scrape_pdf(
     return str(result)
 
 
+@safe_tool_decorator(
+    description="Analyze local codebase and extract code knowledge. Walks directory tree, analyzes code files, extracts signatures, docstrings, and optionally generates API reference documentation."
+)
+async def scrape_codebase(
+    directory: str,
+    output: str = "output/codebase/",
+    depth: str = "deep",
+    languages: str = "",
+    file_patterns: str = "",
+    build_api_reference: bool = False,
+) -> str:
+    """
+    Analyze local codebase and extract code knowledge.
+
+    Args:
+        directory: Directory to analyze (required)
+        output: Output directory for results (default: output/codebase/)
+        depth: Analysis depth - surface, deep, full (default: deep)
+        languages: Comma-separated languages to analyze (e.g., "Python,JavaScript,C++")
+        file_patterns: Comma-separated file patterns (e.g., "*.py,src/**/*.js")
+        build_api_reference: Generate API reference markdown (default: false)
+
+    Returns:
+        Codebase analysis results with file paths.
+    """
+    args = {
+        "directory": directory,
+        "output": output,
+        "depth": depth,
+        "languages": languages,
+        "file_patterns": file_patterns,
+        "build_api_reference": build_api_reference,
+    }
+
+    result = await scrape_codebase_impl(args)
+    if isinstance(result, list) and result:
+        return result[0].text if hasattr(result[0], "text") else str(result[0])
+    return str(result)
+
+
 # ============================================================================
 # PACKAGING TOOLS (3 tools)
 # ============================================================================

src/skill_seekers/mcp/tools/__init__.py

@@ -24,6 +24,7 @@ from .scraping_tools import (
     scrape_docs_tool as scrape_docs_impl,
     scrape_github_tool as scrape_github_impl,
     scrape_pdf_tool as scrape_pdf_impl,
+    scrape_codebase_tool as scrape_codebase_impl,
 )
 
 from .packaging_tools import (
@@ -56,6 +57,7 @@ __all__ = [
     "scrape_docs_impl",
     "scrape_github_impl",
     "scrape_pdf_impl",
+    "scrape_codebase_impl",
     # Packaging tools
     "package_skill_impl",
     "upload_skill_impl",

src/skill_seekers/mcp/tools/scraping_tools.py

@@ -6,6 +6,7 @@ This module contains all scraping-related MCP tool implementations:
 - scrape_docs_tool: Scrape documentation (legacy or unified)
 - scrape_github_tool: Scrape GitHub repositories
 - scrape_pdf_tool: Scrape PDF documentation
+- scrape_codebase_tool: Analyze local codebase and extract code knowledge
 
 Extracted from server.py for better modularity and organization.
 """
@@ -430,3 +431,70 @@ async def scrape_github_tool(args: dict) -> List[TextContent]:
         return [TextContent(type="text", text=output)]
     else:
         return [TextContent(type="text", text=f"{output}\n\n❌ Error:\n{stderr}")]
+
+
+async def scrape_codebase_tool(args: dict) -> List[TextContent]:
+    """
+    Analyze local codebase and extract code knowledge.
+
+    Walks directory tree, analyzes code files, extracts signatures,
+    docstrings, and optionally generates API reference documentation.
+
+    Args:
+        args: Dictionary containing:
+            - directory (str): Directory to analyze
+            - output (str, optional): Output directory for results (default: output/codebase/)
+            - depth (str, optional): Analysis depth - surface, deep, full (default: deep)
+            - languages (str, optional): Comma-separated languages (e.g., "Python,JavaScript,C++")
+            - file_patterns (str, optional): Comma-separated file patterns (e.g., "*.py,src/**/*.js")
+            - build_api_reference (bool, optional): Generate API reference markdown (default: False)
+
+    Returns:
+        List[TextContent]: Tool execution results
+
+    Example:
+        scrape_codebase(
+            directory="/path/to/repo",
+            depth="deep",
+            build_api_reference=True
+        )
+    """
+    directory = args.get("directory")
+    if not directory:
+        return [TextContent(type="text", text="❌ Error: directory parameter is required")]
+
+    output = args.get("output", "output/codebase/")
+    depth = args.get("depth", "deep")
+    languages = args.get("languages", "")
+    file_patterns = args.get("file_patterns", "")
+    build_api_reference = args.get("build_api_reference", False)
+
+    # Build command
+    cmd = [sys.executable, "-m", "skill_seekers.cli.codebase_scraper"]
+    cmd.extend(["--directory", directory])
+
+    if output:
+        cmd.extend(["--output", output])
+    if depth:
+        cmd.extend(["--depth", depth])
+    if languages:
+        cmd.extend(["--languages", languages])
+    if file_patterns:
+        cmd.extend(["--file-patterns", file_patterns])
+    if build_api_reference:
+        cmd.append("--build-api-reference")
+
+    timeout = 600  # 10 minutes for codebase analysis
+
+    progress_msg = "🔍 Analyzing local codebase...\n"
+    progress_msg += f"📁 Directory: {directory}\n"
+    progress_msg += f"⏱️ Maximum time: {timeout // 60} minutes\n\n"
+
+    stdout, stderr, returncode = run_subprocess_with_streaming(cmd, timeout=timeout)
+
+    output_text = progress_msg + stdout
+
+    if returncode == 0:
+        return [TextContent(type="text", text=output_text)]
+    else:
+        return [TextContent(type="text", text=f"{output_text}\n\n❌ Error:\n{stderr}")]

tests/test_mcp_fastmcp.py

@@ -429,6 +429,38 @@ class TestScrapingTools:
 
         assert isinstance(result, str)
 
+    async def test_scrape_codebase_basic(self, temp_dirs):
+        """Test basic codebase scraping."""
+        # Create a dummy source directory
+        src_dir = temp_dirs["output"] / "test_codebase"
+        src_dir.mkdir()
+        (src_dir / "test.py").write_text("def hello(): pass")
+
+        result = await server_fastmcp.scrape_codebase(
+            directory=str(src_dir),
+            output=str(temp_dirs["output"] / "codebase_analysis")
+        )
+
+        assert isinstance(result, str)
+
+    async def test_scrape_codebase_with_options(self, temp_dirs):
+        """Test codebase scraping with various options."""
+        # Create a dummy source directory
+        src_dir = temp_dirs["output"] / "test_codebase2"
+        src_dir.mkdir()
+        (src_dir / "main.py").write_text("class Foo: pass")
+        (src_dir / "utils.js").write_text("function bar() {}")
+
+        result = await server_fastmcp.scrape_codebase(
+            directory=str(src_dir),
+            depth="deep",
+            languages="Python,JavaScript",
+            file_patterns="*.py,*.js",
+            build_api_reference=True
+        )
+
+        assert isinstance(result, str)
+
 
 # ============================================================================
 # PACKAGING TOOLS TESTS (3 tools)