b8fe970493
* fix(mcp): close path traversal + cross-user disclosure in MCP endpoint (PVR0754098)
Path-containment on the storage service was only enforced in save_file;
get_file/get_file_stream/delete_file/get_file_size all resolved user-supplied
names directly, letting an authenticated user read arbitrary files via the
MCP resources/read handler. resources/list and tools/list additionally
returned every user's flows regardless of ownership.
- storage/local.py: extract path-containment into shared _validated_path()
and call it from every read/write/delete entry point (langflow + lfx).
- mcp_utils.handle_read_resource: reject filenames containing ../, /, \ at
the handler layer; require a current user and verify flow ownership
(or self-owned user bucket) before dispatching to storage.
- mcp_utils.handle_read_resource: accept optional project_id so project
servers can't read resources outside the project's flows.
- mcp_projects: pass project_id into handle_read_resource.
- mcp_utils.handle_list_resources / handle_list_tools: scope flow queries
to the authenticated user on the global server.
Regression tests cover traversal rejection on every read path, cross-user
flow access denial, project-scope enforcement, and unauthenticated list
queries returning empty.
* fix(mcp): drop user-bucket files from project-scoped resources/list
Project-scoped handle_list_resources still appended every UserFile owned
by the caller, so a project MCP client could enumerate user-level files
unrelated to the project. User files have no project association, so
skip them entirely when project_id is set.
Adds a regression test proving that project-scoped resources/list returns
only files from flows in the project.
(cherry picked from commit f0fd436fe9)
Langflow is a powerful platform for building and deploying AI-powered agents and workflows. It provides developers with both a visual authoring experience and built-in API and MCP servers that turn every workflow into a tool that can be integrated into applications built on any framework or stack. Langflow comes with batteries included and supports all major LLMs, vector databases and a growing library of AI tools.
✨ Highlight features
- Visual builder interface to quickly get started and iterate.
- Source code access lets you customize any component using Python.
- Interactive playground to immediately test and refine your flows with step-by-step control.
- Multi-agent orchestration with conversation management and retrieval.
- Deploy as an API or export as JSON for Python apps.
- Deploy as an MCP server and turn your flows into tools for MCP clients.
- Observability with LangSmith, LangFuse and other integrations.
- Enterprise-ready security and scalability.
🖥️ Langflow Desktop
Langflow Desktop is the easiest way to get started with Langflow. All dependencies are included, so you don't need to manage Python environments or install packages manually. Available for Windows and macOS.
⚡️ Quickstart
Install locally (recommended)
Requires Python 3.10–3.13 and uv (recommended package manager).
Install
From a fresh directory, run:
uv pip install langflow -U
The latest Langflow package is installed. For more information, see Install and run the Langflow OSS Python package.
Run
To start Langflow, run:
uv run langflow run
Langflow starts at http://127.0.0.1:7860.
That's it! You're ready to build with Langflow! 🎉
📦 Other install options
Run from source
If you've cloned this repository and want to contribute, run this command from the repository root:
make run_cli
For more information, see DEVELOPMENT.md.
Docker
Start a Langflow container with default settings:
docker run -p 7860:7860 langflowai/langflow:latest
Langflow is available at http://localhost:7860/. For configuration options, see the Docker deployment guide.
🛡️ Security
For security information, see our Security Policy.
🚀 Deployment
Langflow is completely open source and you can deploy it to all major deployment clouds. To learn how to deploy Langflow, see our Langflow deployment guides.
⭐ Stay up-to-date
Star Langflow on GitHub to be instantly notified of new releases.
👋 Contribute
We welcome contributions from developers of all levels. If you'd like to contribute, please check our contributing guidelines and help make Langflow more accessible.