mcp-server/spark_executor/tools/fetch_url.py

# coding=utf-8
"""
@Time   :2026/7/9
@Author :tao.chen

Generic HTTP GET proxy for the agent. Lets the agent fetch URLs on the
cluster's network when it cannot reach those hosts directly. Security:
the host is checked against an explicit fnmatch glob allowlist configured
on the connection (`allowed_url_hosts`). Empty or missing allowlist means
no URL access; IP literals and non-HTTP schemes are rejected. Reuses the
connection's saved auth/SSL config so the agent doesn't need cluster credentials.
"""
import ipaddress
import fnmatch
from urllib.parse import urlparse

import httpx

from common.logging import logger
from spark_executor.core.yarn_client import YarnClientConfig
from spark_executor.models import FetchUrlResult
from spark_executor.tools.connections import store as conn_store

_MAX_BODY_BYTES = 1_000_000  # 1 MB cap on response body
_REQUEST_TIMEOUT_SECONDS = 30


def _host_matches_any_glob(host: str, patterns: list[str]) -> bool:
    """True if `host` matches any of the fnmatch glob patterns.

    fnmatch is case-sensitive on Linux (our deployment target). `*` in a
    pattern does NOT cross '.' boundaries, so 'ccam*' matches 'ccam50' but
    NOT 'ccam50.evil.com' (which is what we want — domain boundary matters
    for SSRF).
    """
    host_labels = host.split(".")
    for p in patterns:
        pat_labels = p.split(".")
        if len(pat_labels) != len(host_labels):
            continue
        if all(fnmatch.fnmatchcase(h, pat) for h, pat in zip(host_labels, pat_labels)):
            return True
    return False


def _validate_url_host(
    url: str,
    allowed_hosts: list[str] | None,
) -> None:
    """Raise ValueError if the URL is not allowed to be fetched.

    Allowed only if the URL host matches one of the fnmatch glob patterns in
    `allowed_hosts`. An empty or missing allowlist rejects everything.
    """
    parsed = urlparse(url)
    if parsed.scheme not in ("http", "https"):
        raise ValueError(
            f"URL scheme must be http or https, got {parsed.scheme!r}"
        )
    host = parsed.hostname
    if not host:
        raise ValueError(f"URL has no host: {url!r}")
    # IP literal check
    try:
        ipaddress.ip_address(host)
        raise ValueError(
            f"URL host {host!r} is an IP literal — IP targets are not allowed. "
            f"Use a hostname on the cluster network."
        )
    except ValueError as e:
        if "IP literal" in str(e):
            raise
        # not an IP, continue
    if not allowed_hosts:
        raise ValueError(
            "allowed_url_hosts is empty — set Connection.allowed_url_hosts to "
            "allow specific hosts before calling fetch_url (e.g. ['ccam*'] "
            "for ccam1-ccam99 or ['*.prod.internal'] for a subdomain)."
        )
    if _host_matches_any_glob(host, allowed_hosts):
        return
    raise ValueError(
        f"URL host {host!r} is not in Connection.allowed_url_hosts "
        f"{allowed_hosts!r}. Reject this fetch to prevent SSRF."
    )

def fetch_url(url: str, connection_name: str) -> FetchUrlResult:
    """Proxy an HTTP GET to url using the auth/SSL settings of connection_name."""
    logger.debug(f"fetch_url enter url={url} connection_name={connection_name}")
    conn = conn_store.get(connection_name)
    if conn is None:
        raise KeyError(f"Connection not found: {connection_name}")

    _validate_url_host(url, conn.allowed_url_hosts)

    config = YarnClientConfig.from_connection(conn)
    resp = httpx.get(
        url,
        auth=config.auth_for_httpx(),
        verify=config.verify_for_httpx(),
        timeout=_REQUEST_TIMEOUT_SECONDS,
        follow_redirects=True,
    )

    body = resp.text[:_MAX_BODY_BYTES]
    truncated = len(resp.text) > _MAX_BODY_BYTES

    logger.info(
        f"fetch_url ok url={url} connection_name={connection_name} "
        f"status_code={resp.status_code} "
        f"content_type={resp.headers.get('content-type', '')} "
        f"body_bytes={len(body)} truncated={truncated}"
    )

    return FetchUrlResult(
        url=url,
        status_code=resp.status_code,
        content_type=resp.headers.get("content-type", ""),
        body=body,
        truncated=truncated,
    )