flytohub/flyto-core

v2.5.0 Feature

This release adds 1 notable feature for engineering teams evaluating rollout.

Published 3mo MCP Developer Tools

View tool

✓ No known CVEs patched

Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

ai-agents ai-tools atomic-modules automation browser-automation execution-engine

+12 more

llm low-code mcp mcp-server model-context-protocol playwright python rpa security web-scraping workflow-automation workflow-engine

Affected surfaces

auth

Summary

AI summary

MCP Streamable HTTP Transport enables standard MCP clients to connect to flyto-core via an HTTP endpoint.

Full changelog

What's New

MCP Streamable HTTP Transport — Standard MCP clients (Cursor, Windsurf, etc.) can now connect to flyto-core as a remote MCP server over HTTP.

Remote MCP Server

pip install flyto-core[api]
flyto serve

{
  "mcpServers": {
    "flyto-core": {
      "url": "http://localhost:8333/mcp"
    }
  }
}

Details

POST /mcp — Full JSON-RPC flow: initialize, tools/list, tools/call, ping, notifications, batch requests
DELETE /mcp — Session cleanup
Session management via Mcp-Session-Id header (Streamable HTTP spec)
No auth required on /mcp endpoint (MCP clients don't send Bearer tokens)
STDIO transport (python -m core.mcp_server) unchanged and fully backward-compatible

Internal

Extracted shared MCP logic into mcp_handler.py (transport-independent)
Refactored mcp_server.py as thin STDIO shell over shared handler
Added api/routes/mcp.py for HTTP transport
24 unit tests + 23 integration tests

Closes #4

View diff on GitHub

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Share on X Share on Bluesky

Track flytohub/flyto-core

Get notified when new releases ship.

About flytohub/flyto-core

Deterministic execution engine for AI agents with 412 modules across 78 categories (browser, file, Docker, data, crypto, scheduling). Features execution trace, evidence snapshots, replay from any step, and supports both STDIO and Streamable HTTP transport.

All releases →