Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

openFlow

REMOTE · OPENFLOWMCP.COM

Omni Flash and Veo video, Nano Banana images on Google Flow, from any MCP client

Available components

0 this week 88 Trust /100

Last scanned (14 minutes ago)

Scores higher than 96% of remote servers

Reachable. Last reached 5 Nov 2026.

Category Design and Media

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security89
Transport & Reachability100
Schema Quality & AI Usability70
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 16734 tokens (~321/item across 52 items; 51 tools + 1 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage67
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 0% of tool parameters carry a description.Fail
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 51 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 53 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
  • Supports UI / widget rendering.Pass
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 29 Oct 26 0
    • Tool “generate_voice” rewrote its description, which is the text the model reads security
  • 28 Oct 26 0
    • Tool “check_job” rewrote its description, which is the text the model reads security
  • 27 Oct 26 0
    • Tool “generate_image” rewrote its description, which is the text the model reads security
    • Tool “generate_video” rewrote its description, which is the text the model reads security
    • Tool “generate_voice” rewrote its description, which is the text the model reads security
    • “generate_image” added an optional parameter “idempotency_key” cosmetic
    • “generate_video” added an optional parameter “idempotency_key” cosmetic
    • “generate_voice” added an optional parameter “idempotency_key” cosmetic
  • 24 Oct 26 0
    • Tool “chat_gemini_flash” rewrote its description, which is the text the model reads security
    • Tool “chat_gemini_pro” rewrote its description, which is the text the model reads security
    • “chat_gemini_flash” added an optional parameter “max_tokens” cosmetic
    • “chat_gemini_flash” added an optional parameter “thinking_budget” cosmetic
    • “chat_gemini_flash” added an optional parameter “thinking_level” cosmetic
    • “chat_gemini_pro” added an optional parameter “thinking_budget” cosmetic
    • “chat_gemini_pro” added an optional parameter “thinking_level” cosmetic
  • 23 Oct 26 0
    • New tool “contact_support” functional
    • New tool “support_replies” functional
  • 21 Oct 26 +1
    • Tool “flow_status” rewrote its description, which is the text the model reads security
    • New tool “add_antigravity_start” functional
    • New tool “add_antigravity_submit” functional
    • New tool “complete_antigravity_account” functional
    • New tool “list_llm_accounts” functional
  • 20 Oct 26 0
    • Tool “fetch_media” rewrote its description, which is the text the model reads security
    • Tool “flow_health” rewrote its description, which is the text the model reads security
  • 17 Oct 26 0
    • Tool “edit_video” rewrote its description, which is the text the model reads security
    • Tool “fetch_media” rewrote its description, which is the text the model reads security
    • Tool “generate_image” rewrote its description, which is the text the model reads security
    • Tool “generate_scene” rewrote its description, which is the text the model reads security
    • Tool “generate_video_from_image” rewrote its description, which is the text the model reads security
    • Tool “generate_video_with_reference” rewrote its description, which is the text the model reads security
    • “generate_video_from_image” added an optional parameter “frame” cosmetic
    • “generate_video_from_image” added an optional parameter “start_media_id” cosmetic
    • “generate_video_from_image” made “start_image_base64” optional cosmetic
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 5 Nov 2026 · Probed https://openflowmcp.com/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=openflowmcp.com CN=YE1,O=Let's Encrypt,C=US 23 Sept 2026 22 Dec 2026 ECDSA 256 ECDSA-SHA384 5a2c55ffdbd75dd80f4dc8d0470ea1495dd
SANs: openflowmcp.com, www.openflowmcp.com
CN=YE1,O=Let's Encrypt,C=US (CA) CN=Root YE,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 ECDSA 384 ECDSA-SHA384 5ddd70dd31f801c85c186a7a04b80afe
CN=Root YE,O=ISRG,C=US (CA) CN=ISRG Root X2,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 ECDSA-SHA384 872165fc34b6e5fba8add5b3705fb53a
CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 SHA256-RSA 6c8f1dc727c7117f7baf853ac980f9cd

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of openflowmcp.com. — Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
com. present 19718 13 Verified
openflowmcp.com. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication Enforced and verified

The endpoint asked for a token and published valid RFC 9728 metadata describing how to get one.

Result Enforced and verified
Enforced On tool calls
HTTP status 200

WWW-Authenticate challenge Bearer realm="openFlow", error="invalid_token", error_description="No API key was sent. openFlow needs one.", resource_metadata="https://openflowmcp.com/.well-known/oauth-protected-resource"

Bearer realm="openFlow", error="invalid_token", error_description="No API key was sent. openFlow needs one.", resource_metadata="https://openflowmcp.com/.well-known/oauth-protected-resource"

Protected resource metadata

Document https://openflowmcp.com/.well-known/oauth-protected-resource
Retrieved Yes
Resource https://openflowmcp.com/mcp
Authorisation server https://openflowmcp.com

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://openflowmcp.com/mcp Verified 200
http (plaintext) http://openflowmcp.com/mcp HTTPS enforced 301 https://openflowmcp.com/mcp
MCP tools · 51 exposed · ~16,358 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
upscale_video ~339

Upscale an existing generated video (from a prior generate_video call) to a higher resolution -- the same "270p/720p/1080p/4K" choice Flow offers when downloading. Counts against the weekly free video limit (3 a week without a subscription), like any other video operation, and spends the account's own Flow credits. account: the Google account whose project owns media_id. Do not guess it and do not ask the user: the generate_video result you already have carries it in the `account_used` field -- pass that value verbatim. A media_id only exists inside the project of the account that produced it, so any other account returns a clean error. target_resolution: "1080p", "4K" or "from_360p" (omni_upsampler_360p -- lifts a 360p draft to normal quality; not yet live-tested). 4K may be locked behind a paid plan tier on some accounts -- comes back as a clean error rather than a crash, just report it. Slower than generation: it is kicked off and then polled like a normal video generation -- returns a job_id to poll with check_job if it is not done within ~40s. Returns {"media_id": <new upscaled mediaId>, "download_path": "/v1/media/....mp4", "resolution": ...} when done.

NameTypeReqDescription
accountstringyes–
media_idstringyes–
target_resolutionstring––

No output schema declared.

No examples provided.

Install

How do I install the openFlow MCP server?

openFlow is a hosted endpoint at https://openflowmcp.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · openflowmcp.com

# add to Claude Code
claude mcp add --transport http molkex-omni-flash-veo3-nano-banana 'https://openflowmcp.com/mcp'
Common questions

What is the openFlow MCP server?

openFlow is an MCP server listed in the public MCP registry as io.github.molkex/omni-flash-veo3-nano-banana. Omni Flash and Veo video, Nano Banana images on Google Flow, from any MCP client. This page covers its hosted endpoint (https://openflowmcp.com/mcp).

Is the openFlow MCP server safe to use?

openFlow scores 88 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the openFlow MCP server expose?

openFlow exposes 51 tools: generate_with_face, generate_image, music_generate, music_chat, music_stems, and 46 more. Their descriptions and schemas cost roughly 16,358 tokens of context every time the server is loaded.

Does the openFlow MCP server require authentication?

Yes. openFlow asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

Is the openFlow MCP server still maintained?

openFlow is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.