Flyto Core

Name: Flyto Core
Author: flytohub

by flytohubcommunityv2.12.6

264

flyto-core is a debuggable automation engine that allows users to trace every step of their workflows and replay from any point. It integrates browser automation with structured execution and evidence capture.

From the registry: Execution engine for AI agents. 412 modules: browser, file, Docker, data, crypto.

GitHub Repository

Install & configure

Prerequisites

required
Install flyto-core
Install via pip (add [browser] extra for Playwright)
```
$ pip install flyto-core
```
https://pypi.org/project/flyto-core/

optional

Install browser (optional)

For browser automation modules

$ pip install flyto-core[browser] && playwright install chromium

Install in your client

Paste into the AI you're chatting with — it will figure out the rest

Please install the `flyto-core` MCP server into my current AI client (that's you).

Required prerequisites (do these first if not already done):
- **Install flyto-core** — Install via pip (add [browser] extra for Playwright) Run: `pip install flyto-core` (https://pypi.org/project/flyto-core/)

Optional prerequisites:
- Install browser (optional) — For browser automation modules Run: `pip install flyto-core[browser] && playwright install chromium`

Canonical MCP server config (stdio transport):
- command: `python`
- args: ["-m","core.mcp_server"]

Note: Debuggable automation engine with 467 modules. Also exposes an HTTP MCP transport via 'flyto serve' (POST /mcp). Hosted deployment available at Fronteir AI.

Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.

Note: Debuggable automation engine with 467 modules. Also exposes an HTTP MCP transport via 'flyto serve' (POST /mcp). Hosted deployment available at Fronteir AI.