3e1469a55a* Rebuild Studio branch on top of main * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Fix security and code quality issues for Studio PR #4237 - Validate models_dir query param against allowed directory roots to prevent path traversal in /api/models/local endpoint - Replace string startswith() with Path.is_relative_to() for frontend path traversal check in serve_frontend - Sanitize SSE error messages to not leak exception details to clients (4 locations in inference.py) - Bind port-discovery socket to 127.0.0.1 instead of all interfaces in llama_cpp backend - Import datasets_root and resolve_output_dir in embedding training function to fix NameError and use managed output directory - Remove stale .gitignore entries for package-lock.json and test directories so tests can be tracked in version control - Add venv-reexecution logic to ui CLI command matching the studio command behavior * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Move models_dir path validation before try/except block The HTTPException(403) was inside the try/except Exception handler, so it would be caught and re-raised as a 500. Moving the validation before the try block ensures the 403 is returned directly and also makes the control flow clearer for static analysis (path is validated before any filesystem operations). * Use os.path.realpath + startswith for models_dir validation CodeQL py/path-injection does not recognize Path.is_relative_to() as a sanitizer. Switched to os.path.realpath + str.startswith which is a recognized sanitizer pattern in CodeQL's taint analysis. The startswith check uses root_str + os.sep to prevent prefix collisions (e.g. /app/models_evil matching /app/models). * Never pass user input to Path constructor in models_dir validation CodeQL traces taint through Path(resolved) even after a startswith barrier guard. Fix: the user-supplied models_dir is only used as a string for comparison against allowed roots. The Path object passed to _scan_models_dir comes from the trusted allowed_roots list, not from user input. This fully breaks the taint chain. --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
82 lines
2.6 KiB
Python
82 lines
2.6 KiB
Python
# SPDX-License-Identifier: AGPL-3.0-only
|
|
# Copyright 2026-present the Unsloth AI Inc. team. All rights reserved. See /studio/LICENSE.AGPL-3.0
|
|
|
|
"""MCP helper endpoints for data recipe."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from collections import defaultdict
|
|
|
|
from fastapi import APIRouter
|
|
|
|
from core.data_recipe.service import build_mcp_providers
|
|
from models.data_recipe import (
|
|
McpToolsListRequest,
|
|
McpToolsListResponse,
|
|
McpToolsProviderResult,
|
|
)
|
|
|
|
router = APIRouter()
|
|
|
|
|
|
@router.post("/mcp/tools", response_model = McpToolsListResponse)
|
|
def list_mcp_tools(payload: McpToolsListRequest) -> McpToolsListResponse:
|
|
try:
|
|
from data_designer.engine.mcp import io as mcp_io
|
|
except ImportError as exc:
|
|
return McpToolsListResponse(
|
|
providers = [
|
|
McpToolsProviderResult(
|
|
name = "",
|
|
error = f"MCP dependencies unavailable: {exc}",
|
|
)
|
|
]
|
|
)
|
|
|
|
providers: list[McpToolsProviderResult] = []
|
|
tool_to_providers: dict[str, list[str]] = defaultdict(list)
|
|
|
|
for provider_payload in payload.mcp_providers:
|
|
provider_name = str(provider_payload.get("name", "")).strip()
|
|
built = build_mcp_providers({"mcp_providers": [provider_payload]})
|
|
if len(built) != 1:
|
|
providers.append(
|
|
McpToolsProviderResult(
|
|
name = provider_name,
|
|
error = "Unsupported MCP provider config.",
|
|
)
|
|
)
|
|
continue
|
|
|
|
provider = built[0]
|
|
try:
|
|
tools = mcp_io.list_tools(provider, timeout_sec = payload.timeout_sec)
|
|
tool_names = sorted(
|
|
{tool.name for tool in tools if getattr(tool, "name", "")}
|
|
)
|
|
for tool_name in tool_names:
|
|
tool_to_providers[tool_name].append(provider.name)
|
|
providers.append(
|
|
McpToolsProviderResult(
|
|
name = provider.name,
|
|
tools = tool_names,
|
|
)
|
|
)
|
|
except Exception as exc:
|
|
providers.append(
|
|
McpToolsProviderResult(
|
|
name = provider.name or provider_name,
|
|
error = str(exc).strip() or "Failed to load tools.",
|
|
)
|
|
)
|
|
|
|
duplicate_tools = {
|
|
tool_name: provider_names
|
|
for tool_name, provider_names in sorted(tool_to_providers.items())
|
|
if len(provider_names) > 1
|
|
}
|
|
|
|
return McpToolsListResponse(
|
|
providers = providers,
|
|
duplicate_tools = duplicate_tools,
|
|
)
|