index_prisma_api_docs

Instructions

Implementation Reference

• src/main.py:219-223 (handler)

  The @mcp.tool decorated handler function that implements the index_prisma_api_docs tool by invoking the DocumentationIndexer.index_site method for the 'prisma_api' site.

  @mcp.tool()
  async def index_prisma_api_docs(max_pages: int = 50) -> str:
      """Index Prisma Cloud API documentation. Call this first before searching."""
      pages_indexed = await indexer.index_site('prisma_api', max_pages)
      return f"Indexed {pages_indexed} pages from Prisma Cloud API documentation"

• src/main.py:39-106 (helper)

  Supporting helper method in DocumentationIndexer class that performs web crawling, parsing, and caching of documentation pages from the specified site (e.g., 'prisma_api'). This is the core logic executed by the tool handler.

  async def index_site(self, site_name: str, max_pages: int = 100):
      """Index documentation from a specific site"""
      if site_name not in self.base_urls:
          raise ValueError(f"Unknown site: {site_name}")
      
      base_url = self.base_urls[site_name]
      visited_urls = set()
      urls_to_visit = [base_url]
      pages_indexed = 0
      
      async with aiohttp.ClientSession() as session:
          while urls_to_visit and pages_indexed < max_pages:
              url = urls_to_visit.pop(0)
              
              if url in visited_urls:
                  continue
                  
              visited_urls.add(url)
              
              try:
                  async with session.get(url, timeout=10) as response:
                      if response.status == 200:
                          content = await response.text()
                          soup = BeautifulSoup(content, 'html.parser')
                          
                          # Extract page content
                          title = soup.find('title')
                          title_text = title.text.strip() if title else url
                          
                          # Remove script and style elements
                          for script in soup(["script", "style"]):
                              script.decompose()
                          
                          # Get text content
                          text_content = soup.get_text()
                          lines = (line.strip() for line in text_content.splitlines())
                          chunks = (phrase.strip() for line in lines for phrase in line.split("  "))
                          text = ' '.join(chunk for chunk in chunks if chunk)
                          
                          # Store in cache
                          self.cached_pages[url] = CachedPage(
                              title=title_text,
                              content=text[:5000],  # Limit content length
                              url=url,
                              site=site_name,
                              timestamp=time.time()
                          )
                          
                          pages_indexed += 1
                          
                          # Find more links to index
                          if pages_indexed < max_pages:
                              links = soup.find_all('a', href=True)
                              for link in links:
                                  href = link['href']
                                  full_url = urljoin(url, href)
                                  
                                  # Only index URLs from the same domain
                                  if urlparse(full_url).netloc == urlparse(base_url).netloc:
                                      if full_url not in visited_urls and full_url not in urls_to_visit_set:
                                          urls_to_visit.append(full_url)
                                          urls_to_visit_set.add(full_url)
                              
              except Exception as e:
                  print(f"Error indexing {url}: {e}")
                  continue
      
      return pages_indexed

• src/main.py:16-27 (helper)

  Dataclass used by the indexer to store cached page data with expiration logic.

  @dataclass
  class CachedPage:
      title: str
      content: str
      url: str
      site: str
      timestamp: float
      ttl: float = 3600  # 1 hour default TTL
      
      @property
      def is_expired(self) -> bool:
          return time.time() > self.timestamp + self.ttl

• src/main.py:219-219 (registration)

  MCP tool registration decorator for the index_prisma_api_docs function.

  @mcp.tool()