# OpenFlow > An AI agent harness built for workflows. - **Type:** MCP server - **Install:** `agentstack add mcp-philbotar-openflow` - **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior - **Seller:** [philbotar](https://agentstack.voostack.com/s/philbotar) - **Installs:** 0 - **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml) - **Latest version:** 0.1.0 - **License:** MIT - **Upstream author:** [philbotar](https://github.com/philbotar) - **Source:** https://github.com/philbotar/OpenFlow ## Install ```sh agentstack add mcp-philbotar-openflow ``` Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent. ## About OpenFlow Compose and run AI agent workflows, visually. An agent harness built for repeatable workflows, with the extensibility and feel of Claude Code. Quick Start · Screenshots · Features · Architecture · Development · Contributing ## Quick Start ### Prerequisites - [Rust](https://rustup.rs/) (stable) - [Node.js](https://nodejs.org/) 18+ - Platform build tools for [Tauri](https://v2.tauri.app/start/prerequisites/) ### Run ```bash ./scripts/start.sh ``` Installs dependencies on first run, then launches the desktop app. ### Install (macOS) ```bash ./scripts/install.sh ``` Builds a `.dmg` and opens it — drag **OpenFlow** to **Applications**. > **macOS gatekeeper:** Unsigned local builds may be blocked on first launch. Right-click **OpenFlow** → **Open**, or run `xattr -cr /path/to/OpenFlow.app`. --- ## Screenshots Run a multi-agent pipeline — parallel layers, live status, and per-node conversation. Configure reusable agents — model, prompts, JSON schema, and tool approval. Describe a workflow in natural language, iterate, then apply to the editor. ## Features ### Visual workflow editor Drag nodes onto a canvas, wire them into a DAG, and configure each agent in an inspector panel. Validation runs before every run: cycles and broken edges never reach execution. ### Parallel agent layers Nodes in the same topological layer run concurrently. Downstream agents receive upstream output automatically, with no manual plumbing. ### Tools & subagents Built-in filesystem, shell, and search tools with tiered approval policies. Nodes can invoke saved agents as subagents mid-run. ### Multi-provider LLM support OpenAI-compatible and Anthropic adapters behind a single `AiPort`. Swap models per node or override at the workflow level. ### Project-aware persistence Workflows live in the app store or in-repo under `.flow/workflows/`. Projects bind a repo path so agents run with the right working directory. ### Interactive runs Pause, resume, approve tools, and chat with individual nodes. Per-node conversation panels stream thinking, tool calls, and results in real time. ## Architecture OpenFlow uses nested hexagonal architecture: five layers, dependencies pointing strictly inward, enforced in CI. ``` ┌─────────────────────────────────────────────────────────┐ │ UI (React + TypeScript) crates/ui │ ├─────────────────────────────────────────────────────────┤ │ Desktop adapter (Tauri IPC) crates/desktop │ ├─────────────────────────────────────────────────────────┤ │ Orchestration (runs, storage) crates/orchestration│ ├──────────────────────────┬──────────────────────────────┤ │ Engine (I/O-free core) │ Providers (LLM transport) │ │ crates/engine │ crates/providers │ └──────────────────────────┴──────────────────────────────┘ ``` | Crate | Responsibility | | --- | --- | | **engine** | Workflow model, DAG validation, run state machine, ports | | **orchestration** | Persistence, run coordination, tool execution, composition root | | **providers** | OpenAI-compatible and Anthropic wire adapters | | **desktop** | Tauri commands and IPC boundary | | **ui** | Canvas, conversation panels, settings, workflow editor | Deep dive: [`docs/architecture/technical-overview.md`](docs/architecture/technical-overview.md) ## Development ```bash # Full verification gate (fmt, clippy, test, arch, UI typecheck, …) ./scripts/verify.sh # Frontend only (hot reload, no Tauri shell) npm --prefix crates/ui run dev # Frontend typecheck npm --prefix crates/ui run typecheck # Workflow acceptance tests cargo test -p orchestration --test workflow_acceptance -- --nocapture ``` | Resource | Path | | --- | --- | | Repo map & change paths | [`AGENTS.md`](AGENTS.md) | | Coding patterns | [`docs/contributing/coding-patterns.md`](docs/contributing/coding-patterns.md) | | Testing workflows | [`docs/contributing/testing-workflows.md`](docs/contributing/testing-workflows.md) | | Domain glossary | [`docs/glossary.md`](docs/glossary.md) | | Layer contract | [`docs/architecture/contract.md`](docs/architecture/contract.md) | ## Contributing See [`CONTRIBUTING.md`](CONTRIBUTING.md) for the PR checklist. Classify your change with [`docs/contributing/development-lanes.md`](docs/contributing/development-lanes.md), run `./scripts/verify.sh`, and update [`CHANGELOG.md`](CHANGELOG.md) for user-visible changes. ## License [MIT](LICENSE) ## Source & license This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code. - **Author:** [philbotar](https://github.com/philbotar) - **Source:** [philbotar/OpenFlow](https://github.com/philbotar/OpenFlow) - **License:** MIT Install and usage instructions live in the source repository linked above. ## Pricing - **Free** — Free ## Security capabilities Automated source analysis of v0.1.0 — what this tool can access: - **Network access:** no - **Filesystem access:** no - **Shell / process execution:** no - **Environment & secrets:** no - **Dynamic code execution:** no *"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.* ## Versions - **0.1.0** — security scan: passed — Imported from the upstream source. ## Links - Listing page: https://agentstack.voostack.com/l/mcp-philbotar-openflow - Seller: https://agentstack.voostack.com/s/philbotar - Browse the marketplace: https://agentstack.voostack.com/browse --- Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.