feat: add review_pending_changes tool and enforce absolute path security
- Add new review_pending_changes tool for comprehensive pre-commit reviews - Implement filesystem sandboxing with MCP_PROJECT_ROOT - Enforce absolute paths for all file/directory operations - Add comprehensive git utilities for repository management - Update all tools to use centralized path validation - Add extensive test coverage for new features and security model - Update documentation with new tool and path requirements - Remove obsolete demo and guide files 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
Fahad
@@ -5,9 +5,21 @@ File reading utilities with directory support and token management
|
||||
import os
|
||||
from pathlib import Path
|
||||
from typing import List, Optional, Tuple, Set
|
||||
import sys
|
||||
|
||||
from .token_utils import estimate_tokens, MAX_CONTEXT_TOKENS
|
||||
|
||||
# Get project root from environment or use current directory
|
||||
# This defines the sandbox directory where file access is allowed
|
||||
PROJECT_ROOT = Path(os.environ.get("MCP_PROJECT_ROOT", os.getcwd())).resolve()
|
||||
|
||||
# Security: Prevent running with overly permissive root
|
||||
if str(PROJECT_ROOT) == "/":
|
||||
raise RuntimeError(
|
||||
"Security Error: MCP_PROJECT_ROOT cannot be set to '/'. "
|
||||
"This would give access to the entire filesystem."
|
||||
)
|
||||
|
||||
|
||||
# Common code file extensions
|
||||
CODE_EXTENSIONS = {
|
||||
@@ -60,6 +72,46 @@ CODE_EXTENSIONS = {
|
||||
}
|
||||
|
||||
|
||||
def resolve_and_validate_path(path_str: str) -> Path:
|
||||
"""
|
||||
Validates that a path is absolute and resolves it.
|
||||
|
||||
Args:
|
||||
path_str: Path string (must be absolute)
|
||||
|
||||
Returns:
|
||||
Resolved Path object
|
||||
|
||||
Raises:
|
||||
ValueError: If path is not absolute
|
||||
PermissionError: If path is outside allowed directory
|
||||
"""
|
||||
# Create a Path object from the user-provided path
|
||||
user_path = Path(path_str)
|
||||
|
||||
# Require absolute paths
|
||||
if not user_path.is_absolute():
|
||||
raise ValueError(
|
||||
f"Relative paths are not supported. Please provide an absolute path.\n"
|
||||
f"Received: {path_str}"
|
||||
)
|
||||
|
||||
# Resolve the absolute path
|
||||
resolved_path = user_path.resolve()
|
||||
|
||||
# Security check: ensure the resolved path is within PROJECT_ROOT
|
||||
try:
|
||||
resolved_path.relative_to(PROJECT_ROOT)
|
||||
except ValueError:
|
||||
raise PermissionError(
|
||||
f"Path outside project root: {path_str}\n"
|
||||
f"Project root: {PROJECT_ROOT}\n"
|
||||
f"Resolved path: {resolved_path}"
|
||||
)
|
||||
|
||||
return resolved_path
|
||||
|
||||
|
||||
def expand_paths(paths: List[str], extensions: Optional[Set[str]] = None) -> List[str]:
|
||||
"""
|
||||
Expand paths to individual files, handling both files and directories.
|
||||
@@ -78,7 +130,11 @@ def expand_paths(paths: List[str], extensions: Optional[Set[str]] = None) -> Lis
|
||||
seen = set()
|
||||
|
||||
for path in paths:
|
||||
path_obj = Path(path)
|
||||
try:
|
||||
path_obj = resolve_and_validate_path(path)
|
||||
except (ValueError, PermissionError):
|
||||
# Skip invalid paths
|
||||
continue
|
||||
|
||||
if not path_obj.exists():
|
||||
continue
|
||||
@@ -121,13 +177,17 @@ def read_file_content(file_path: str, max_size: int = 1_000_000) -> Tuple[str, i
|
||||
Read a single file and format it for Gemini.
|
||||
|
||||
Args:
|
||||
file_path: Path to file
|
||||
file_path: Path to file (must be absolute)
|
||||
max_size: Maximum file size to read
|
||||
|
||||
Returns:
|
||||
(formatted_content, estimated_tokens)
|
||||
"""
|
||||
path = Path(file_path)
|
||||
try:
|
||||
path = resolve_and_validate_path(file_path)
|
||||
except (ValueError, PermissionError) as e:
|
||||
content = f"\n--- ERROR ACCESSING FILE: {file_path} ---\nError: {str(e)}\n--- END FILE ---\n"
|
||||
return content, estimate_tokens(content)
|
||||
|
||||
try:
|
||||
# Check if path exists and is a file
|
||||
|
||||
164
utils/git_utils.py
Normal file
164
utils/git_utils.py
Normal file
@@ -0,0 +1,164 @@
|
||||
"""
|
||||
Git utilities for finding repositories and generating diffs.
|
||||
"""
|
||||
|
||||
import os
|
||||
import subprocess
|
||||
from typing import Dict, List, Optional, Tuple
|
||||
from pathlib import Path
|
||||
|
||||
|
||||
# Directories to ignore when searching for git repositories
|
||||
IGNORED_DIRS = {
|
||||
"node_modules",
|
||||
"__pycache__",
|
||||
"venv",
|
||||
"env",
|
||||
"build",
|
||||
"dist",
|
||||
"target",
|
||||
".tox",
|
||||
".pytest_cache",
|
||||
}
|
||||
|
||||
|
||||
def find_git_repositories(start_path: str, max_depth: int = 5) -> List[str]:
|
||||
"""
|
||||
Recursively find all git repositories starting from the given path.
|
||||
|
||||
Args:
|
||||
start_path: Directory to start searching from
|
||||
max_depth: Maximum depth to search (prevents excessive recursion)
|
||||
|
||||
Returns:
|
||||
List of absolute paths to git repositories
|
||||
"""
|
||||
repositories = []
|
||||
start_path = Path(start_path).resolve()
|
||||
|
||||
def _find_repos(current_path: Path, current_depth: int):
|
||||
if current_depth > max_depth:
|
||||
return
|
||||
|
||||
try:
|
||||
# Check if current directory is a git repo
|
||||
git_dir = current_path / ".git"
|
||||
if git_dir.exists() and git_dir.is_dir():
|
||||
repositories.append(str(current_path))
|
||||
# Don't search inside .git directory
|
||||
return
|
||||
|
||||
# Search subdirectories
|
||||
for item in current_path.iterdir():
|
||||
if item.is_dir() and not item.name.startswith("."):
|
||||
# Skip common non-code directories
|
||||
if item.name in IGNORED_DIRS:
|
||||
continue
|
||||
_find_repos(item, current_depth + 1)
|
||||
|
||||
except PermissionError:
|
||||
# Skip directories we can't access
|
||||
pass
|
||||
|
||||
_find_repos(start_path, 0)
|
||||
return sorted(repositories)
|
||||
|
||||
|
||||
def run_git_command(repo_path: str, command: List[str]) -> Tuple[bool, str]:
|
||||
"""
|
||||
Run a git command in the specified repository.
|
||||
|
||||
Args:
|
||||
repo_path: Path to the git repository
|
||||
command: Git command as a list of arguments
|
||||
|
||||
Returns:
|
||||
Tuple of (success, output/error)
|
||||
"""
|
||||
try:
|
||||
result = subprocess.run(
|
||||
["git"] + command, cwd=repo_path, capture_output=True, text=True, timeout=30
|
||||
)
|
||||
|
||||
if result.returncode == 0:
|
||||
return True, result.stdout
|
||||
else:
|
||||
return False, result.stderr
|
||||
|
||||
except subprocess.TimeoutExpired:
|
||||
return False, "Command timed out"
|
||||
except Exception as e:
|
||||
return False, str(e)
|
||||
|
||||
|
||||
def get_git_status(repo_path: str) -> Dict[str, any]:
|
||||
"""
|
||||
Get the current git status of a repository.
|
||||
|
||||
Args:
|
||||
repo_path: Path to the git repository
|
||||
|
||||
Returns:
|
||||
Dictionary with status information
|
||||
"""
|
||||
status = {
|
||||
"branch": "",
|
||||
"ahead": 0,
|
||||
"behind": 0,
|
||||
"staged_files": [],
|
||||
"unstaged_files": [],
|
||||
"untracked_files": [],
|
||||
}
|
||||
|
||||
# Get current branch
|
||||
success, branch = run_git_command(repo_path, ["branch", "--show-current"])
|
||||
if success:
|
||||
status["branch"] = branch.strip()
|
||||
|
||||
# Get ahead/behind info
|
||||
if status["branch"]:
|
||||
success, ahead_behind = run_git_command(
|
||||
repo_path,
|
||||
[
|
||||
"rev-list",
|
||||
"--count",
|
||||
"--left-right",
|
||||
f'{status["branch"]}@{{upstream}}...HEAD',
|
||||
],
|
||||
)
|
||||
if success:
|
||||
if ahead_behind.strip():
|
||||
parts = ahead_behind.strip().split()
|
||||
if len(parts) == 2:
|
||||
status["behind"] = int(parts[0])
|
||||
status["ahead"] = int(parts[1])
|
||||
# else: Could not get ahead/behind status (branch may not have upstream)
|
||||
|
||||
# Get file status
|
||||
success, status_output = run_git_command(repo_path, ["status", "--porcelain"])
|
||||
if success:
|
||||
for line in status_output.strip().split("\n"):
|
||||
if not line:
|
||||
continue
|
||||
|
||||
status_code = line[:2]
|
||||
path_info = line[3:]
|
||||
|
||||
# Handle staged changes
|
||||
if status_code[0] == "R":
|
||||
# Format is "old_path -> new_path" for renamed files
|
||||
if " -> " in path_info:
|
||||
_, new_path = path_info.split(" -> ", 1)
|
||||
status["staged_files"].append(new_path)
|
||||
else:
|
||||
status["staged_files"].append(path_info)
|
||||
elif status_code[0] in ["M", "A", "D", "C"]:
|
||||
status["staged_files"].append(path_info)
|
||||
|
||||
# Handle unstaged changes
|
||||
if status_code[1] in ["M", "D"]:
|
||||
status["unstaged_files"].append(path_info)
|
||||
elif status_code == "??":
|
||||
status["untracked_files"].append(path_info)
|
||||
|
||||
return status
|
||||
Reference in New Issue
Block a user