Log inSubmit server
Flyto Core logo

Flyto Core

by flytohub

Runs deterministic agent workflows with browser, API, file, data, and testing modules over MCP.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Flyto Core

Pick your client, then add it in one click or paste the config.

STDIOPython
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "flytohub-flyto-core": {
      "command": "uvx",
      "args": [
        "flyto-core"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Install not yet sandbox-tested— we haven't run this command through our automated sandbox yet. Not a red flag; we're working through the catalog.

Overview

flytohub/flyto-core provides Flyto2's Python execution engine as an MCP-accessible workflow runtime. It exposes modules for browser automation, API calls, files, data, tests, and other tasks, alongside YAML workflows and built-in recipes. Runs produce execution records with evidence checks, checkpoints, and replay support for inspecting or repeating safe steps. Reach for it when an agent needs repeatable multi-step execution through STDIO or Streamable HTTP.

Use cases

  • Run browser-based research workflows
  • Collect website data and save reports
  • Execute repeatable YAML automations
  • Inspect failed workflow steps
  • Replay safe workflow checkpoints

Key features

  • MCP over STDIO and Streamable HTTP
  • Browser, API, file, data, and test modules
  • YAML workflows and built-in recipes
  • Execution traces and evidence records
  • Checkpoint and replay support
  • Python, CLI, and local HTTP access

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked Today

Recent health check succeeded.

21/21 checks healthy over the last 80d

Supply-chain signal

8 high-severity advisories on record for this package. Most advisories affect transitive dependencies and may not be exploitable in this server's actual usage — this is a directional signal, not a security audit.

Critical 2High 6Medium 0Low 8

Scanned 15h ago via OSV.dev · flyto-core (PyPI)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars484Stargazers on the source repository.
Last commit2d agoMost recent push to the default branch.
Directory activity3 viewsConfig copies, upvotes, and views on AllMCPs.

How Flyto Core works

What flytohub/flyto-core does

flytohub/flyto-core is the Python execution engine behind Flyto2. It lets an AI client invoke workflow steps through MCP, while also supporting direct Python use, YAML workflow files, and a local HTTP API. The module inventory covers browser operations, API requests, file handling, data work, tests, and other automation tasks.

The package also includes built-in recipes for repeatable workflows. A recipe can open a website, collect information, capture screenshots, and save results without requiring an agent to generate a new prompt for every run. Workflows can be listed, modules can be browsed, and custom YAML workflows can be executed from the command line.

How it works

Each workflow run records its individual steps rather than returning only a final result. The resulting execution history can be inspected when a step fails, and checkpoints provide points from which a workflow can be resumed or replayed where appropriate. Evidence reported by a tool can be checked against the action's contract, preserving a record of what the execution produced.

MCP access is available through the package's MCP server entry point. The server supports STDIO and Streamable HTTP transport, allowing it to run locally or be connected to an MCP-compatible AI client. Device-specific integrations remain outside the core execution engine; for example, the ROS 2 setup uses a separate adapter for TurtleBot3.

Setup and configuration

Install the base package with pip:

Terminal
pip install flyto-core

For browser workflows, install the browser extra and Chromium:

Terminal
pip install "flyto-core[browser]"
playwright install chromium

Start the MCP server with:

bash
python -m core.mcp_server

The command-line interface can display available recipes and modules or run a custom workflow:

bash
flyto recipes
flyto modules
flyto run your-workflow.yaml

Python 3.10 or newer is required. No environment variables are needed for the documented setup.

Tools and capabilities

  • MCP access over STDIO or Streamable HTTP
  • Browser automation with the browser package extra
  • API, file, data, and test-oriented modules
  • YAML workflow execution and built-in recipes
  • Execution traces and step-by-step run records
  • Evidence validation, checkpoints, and replay support
  • Local HTTP API and direct Python invocation

Limitations and notes

Physical-device actions require a trusted host to approve the action. The TurtleBot3 integration uses ROS 2 and Nav2 through a separate adapter; the robot does not run Flyto2 firmware or motor drivers from this repository. The combined physical-robot setup still requires end-to-end hardware sign-off, so the core package should not be treated as a universal plug-and-play robotics layer.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Flyto Core

flytohub/flyto-core is an MCP server that connects AI clients to Flyto2's Python execution engine and exposes workflow, recipe, and module tools for browser, API, file, data, and testing tasks. It records execution evidence and supports checkpoints and replay through MCP over STDIO or Streamable HTTP.

Install it with `pip install flyto-core`, then start it with `python -m core.mcp_server`. Browser workflows additionally require `pip install "flyto-core[browser]"` and `playwright install chromium`. Python 3.10 or newer is required.

Yes. Cursor can connect to flytohub/flyto-core as an MCP server because it provides standard STDIO and Streamable HTTP transports. Configure it in Cursor's MCP settings using the server command or HTTP endpoint appropriate to your deployment.

Yes. Runs retain step-level execution records, and the engine supports checkpoints and replay where replaying the step is safe. Evidence checks and execution history help inspect what happened before repeating the workflow.

It can participate in a TurtleBot3 setup through a separate ROS 2 adapter, but it is not a universal robotics driver. Physical actions require approval from a trusted host, and the combined hardware setup still needs end-to-end sign-off.

Related MCP servers

All in Cloud Platforms All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewFlyto Core AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/flytohub-flyto-core?style=directory)](https://allmcps.com/mcp/flytohub-flyto-core)
HTML Embed
<a href="https://allmcps.com/mcp/flytohub-flyto-core"><img src="https://allmcps.com/api/badge/flytohub-flyto-core?style=directory" alt="Flyto Core on AllMCPs" /></a>