FastMCP Documentation & Web Scraping Server

from fastmcp import FastMCP
import requests
import os
import zipfile
from minsearch import Index

mcp = FastMCP("Demo 🚀")


def fetch_markdown_impl(url: str) -> str:
    """Fetch a web page using Jina reader and return its markdown text.

    The Jina reader endpoint is `https://r.jina.ai/{original_url}`.
    The `url` argument may be a full URL (including scheme) or a hostname/path.
    """
    if not url.startswith("http://") and not url.startswith("https://"):
        url = "https://" + url
    target = "https://r.jina.ai/" + url
    resp = requests.get(target, timeout=15)
    resp.raise_for_status()
    return resp.text


@mcp.tool
def fetch_markdown(url: str) -> str:
    """Return markdown content of a web page via Jina reader."""
    return fetch_markdown_impl(url)


@mcp.tool
def add(a: int, b: int) -> int:
    """Add two numbers"""
    return a + b


# --- minsearch integration for documentation search ---
ZIP_URL = "https://github.com/jlowin/fastmcp/archive/refs/heads/main.zip"
ZIP_NAME = "fastmcp-main.zip"

# simple module-level cache for the built index
_INDEX_CACHE = None


def ensure_zip():
    if os.path.exists(ZIP_NAME):
        return
    resp = requests.get(ZIP_URL, stream=True, timeout=60)
    resp.raise_for_status()
    with open(ZIP_NAME, "wb") as f:
        for chunk in resp.iter_content(1024 * 64):
            if chunk:
                f.write(chunk)


def iter_md_files_from_zip(zip_path):
    with zipfile.ZipFile(zip_path, "r") as z:
        for name in z.namelist():
            lower = name.lower()
            if lower.endswith(".md") or lower.endswith(".mdx"):
                data = z.read(name)
                text = data.decode("utf-8", errors="replace")
                if "/" in name:
                    _, rest = name.split("/", 1)
                else:
                    rest = name
                yield rest, text


def build_index_from_zip():
    docs = []
    ensure_zip()
    for fname in os.listdir('.'):
        if fname.lower().endswith('.zip'):
            for filename, text in iter_md_files_from_zip(fname):
                docs.append({'content': text, 'filename': filename})
    idx = Index(text_fields=["content"], keyword_fields=["filename"])
    idx.fit(docs)
    return idx


def get_index():
    global _INDEX_CACHE
    if _INDEX_CACHE is None:
        _INDEX_CACHE = build_index_from_zip()
    return _INDEX_CACHE


def search_docs_impl(query: str, top_k: int = 5):
    idx = get_index()
    results = idx.search(query, num_results=top_k)
    return results


@mcp.tool
def search_docs(query: str) -> list:
    """Search the documentation index and return top filenames for `query`."""
    results = search_docs_impl(query, top_k=5)
    return [r.get('filename') for r in results]


if __name__ == "__main__":
    mcp.run()