# gflow-cli (pypi · gflow-cli)

Drive Google Flow from an agent: Veo video and Imagen image generation

- Trust score: 68/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- pypi · `gflow-cli`: 68/100 (this document), [markdown](https://verifymcp.io/servers/ffroliva-gflow-cli/gflow-cli.md), [page](https://verifymcp.io/servers/ffroliva-gflow-cli/gflow-cli)

## Channel facts

- Registry: `pypi`
- Package: `gflow-cli`
- Version: `0.79.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-20.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it.
  - 5 of 54 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 35/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - License check failed: the license (MIT License) isn't a recognized OSI-approved license.
  - Actively maintained (last published 1 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 81/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1711 tokens (~90/item across 19 items; 16 tools + 3 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 13/100
  - Stability observed for 4 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "gflow_instructions_rm" implies "rm" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 17 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the gflow-cli MCP server?

gflow-cli runs locally as a PyPI package, launched with uvx gflow-cli. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add ffroliva-gflow-cli -- uvx gflow-cli
```

### Cursor

```json
{
  "mcpServers": {
    "ffroliva-gflow-cli": {
      "command": "uvx",
      "args": [
        "gflow-cli"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ffroliva-gflow-cli": {
      "command": "uvx",
      "args": [
        "gflow-cli"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add ffroliva-gflow-cli -- uvx gflow-cli
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ffroliva-gflow-cli": {
      "type": "local",
      "command": [
        "uvx",
        "gflow-cli"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ffroliva-gflow-cli --command uvx --arg gflow-cli
```

### Hermes

```yaml
mcp_servers:
  ffroliva-gflow-cli:
    command: "uvx"
    args: ["gflow-cli"]
```

### Netclaw

```json
{
  "McpServers": {
    "ffroliva-gflow-cli": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "gflow-cli"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add ffroliva-gflow-cli -t stdio -c uvx -a gflow-cli
```

### Other

```json
{
  "mcpServers": {
    "ffroliva-gflow-cli": {
      "command": "uvx",
      "args": [
        "gflow-cli"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-20 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-19 (score 67, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-09-18 (score 52, −14)

- [security regression] Malware scan: pass → unverified
- [functional] Package version: 0.78.0 → 0.79.0

### 2026-09-17 (score 66, 0)

- [security regression] Tool safety: pass → unverified
- [security] Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet.
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Schema quality: 100 → unverified
- [functional improvement] Stability: unverified → 0.03
- [functional] Package version: 0.77.0 → 0.78.0
- [functional] Package version: 0.77.0 → 0.77.1

### 2026-09-16 (score 66)

First indexed and scored.

## MCP tools (16)

### `gflow_generate_image` (~281 tokens)

Generate an image using Google Flow's Imagen model. Produces 1-4 images from a text prompt. Models: nano2 (fast), nano-pro (balanced), image4 (highest quality). Aspects: 1:1, 9:16, 16:9, 4:3, 3:4. The prompt supports @AssetName mentions to tag saved project characters/assets by name (resolves to referenceEntities/referenceImages). Reference a SAVED named asset via @Name; reference an arbitrary one-off image via reference_images. See docs/REFERENCE_STRATEGIES.md. On accounts served from flow.google.com, use an existing project and local reference files; UUID/entity references and image4 are not ported to that composer yet and fail before submit; retrying will not clear it. Returns local file paths to the generated images.

Input parameters:

- `aspect` (string)
- `count` (integer)
- `instructions`
- `model` (string)
- `output`
- `profile` (string)
- `project`
- `project_name`
- `prompt` (string, required)
- `reference_entities`
- `reference_entity_names`
- `reference_images`
- `seed`
- `tools`
- `ui_mode`
- `wait` (boolean)

### `gflow_generate_video` (~304 tokens)

Generate a video using Google Flow's Veo model. Modes: t2v (text-to-video), i2v (image-to-video), r2v (reference-to-video). Aspects: 9:16, 16:9. Optional model (veo_lite/veo_fast/veo_quality/omni_flash), duration (seconds), and count select the Veo model, clip length, and batch size (CLI parity). The prompt supports @CharacterName mentions to tag saved project characters by name (resolves to referenceEntities). Reference a SAVED character via @Name; pass one-off ingredient images via reference_images. See docs/REFERENCE_STRATEGIES.md. Optional ui_mode ('classic'/'auto') verifies the classic editor pre-submit and aborts before spending credits if unreachable; 'agentic' is not supported for video. Returns the local file path to the generated video.

Input parameters:

- `aspect` (string)
- `count` (integer)
- `duration`
- `end_frame`
- `initial_frame`
- `mode` (string)
- `model`
- `output`
- `profile` (string)
- `project`
- `project_name`
- `prompt` (string, required)
- `reference_entities`
- `reference_entity_names`
- `reference_images`
- `tools`
- `ui_mode`
- `wait` (boolean)

### `gflow_list_tools` (~25 tokens)

List available gflow prompt tools (name, title, description, category).

### `gflow_get_credits` (~70 tokens)

Read the current Google Flow credit balance for one saved profile or all profiles. This is read-only and spends no credits. Set all_profiles=true when choosing an account for generation; partial profile failures remain visible in the result.

Input parameters:

- `all_profiles` (boolean)
- `profile` (string)

### `gflow_character_list` (~103 tokens)

List the saved Flow CHARACTER entities in a project, with their entity ids. Read-only and spends no credits. Call this to discover what you can attach: an id goes to reference_entities on the generate tools, and a display_name can be used as an @Name mention in a prompt (same wire, they dedupe). Drives a browser session, so it is slower than the catalog tools.

Input parameters:

- `profile` (string)
- `project` (string, required)

### `gflow_character_voices` (~49 tokens)

List the preset voices available for a Flow Character's TTS. Static lookup — no network, no browser, no cost. Call it before creating a character to choose a valid voice name.

### `gflow_character_show` (~91 tokens)

Show one saved Flow CHARACTER entity by id or by exact display name. Read-only and spends no credits. Exactly one of entity_id or name is required; an ambiguous name is an error rather than a guess, which is the reason to prefer the id. Drives a browser session.

Input parameters:

- `entity_id`
- `name`
- `profile` (string)
- `project` (string, required)

### `gflow_download_media` (~140 tokens)

Fetch an already-generated VIDEO from Flow by its media ID and write it to disk. For a generation that finished and was billed but whose download failed — the clip is in the Flow project and the local catalog shows no file for it. Spends no credits: the generation was already paid for. The bytes are verified against the size Flow reports before the file is written. Video only: an image media ID is refused immediately (exit 11) because the signed URL this needs comes from a record only a clip's route emits. See issue #877.

Input parameters:

- `media_id` (string, required)
- `out_dir`
- `profile`

### `gflow_list_projects` (~55 tokens)

List all projects in the local gflow catalog. Returns project IDs, names, and creation dates from the SQLite database.

Input parameters:

- `limit` (integer)
- `offset` (integer)
- `profile` (string)

### `gflow_auth_status` (~97 tokens)

Non-interactive, credit-free Flow session probe (#497). Call this BEFORE a generation tool to fail fast on expired auth — the queue is async, so an auth failure otherwise surfaces only later from the daemon. Never starts an interactive login flow; may boot a short-lived headless browser only if cookie decryption requires the Playwright fallback. May take up to ~45s on a slow network.

Input parameters:

- `profile` (string)

### `gflow_instructions_list` (~45 tokens)

List a Flow project's persistent Agent-Mode instruction cards (reads the live server brief). Credits-free.

Input parameters:

- `profile` (string)
- `project` (string, required)

### `gflow_instructions_add` (~97 tokens)

Add a persistent instruction card to a Flow project's Agent-Mode brief (credits-free). Each ref is classified automatically: local image path → uploaded as an image reference; asset UUID → image reference; anything else → character id/name.

Input parameters:

- `enabled` (boolean)
- `profile` (string)
- `project` (string, required)
- `refs`
- `text` (string, required)
- `title` (string, required)

### `gflow_instructions_set_enabled` (~70 tokens)

Enable or disable one instruction card on a Flow project's brief, selected by title or card id (exactly one). Credits-free.

Input parameters:

- `card_id`
- `enabled` (boolean, required)
- `profile` (string)
- `project` (string, required)
- `title`

### `gflow_instructions_rm` (~60 tokens)

Remove one instruction card from a Flow project's brief, selected by title or card id (exactly one). Credits-free.

Input parameters:

- `card_id`
- `profile` (string)
- `project` (string, required)
- `title`

### `gflow_instructions_toggle_mode` (~63 tokens)

Turn a Flow project's brief master switch on or off. When off, NO cards apply even if individually enabled. Cards are left untouched. Credits-free.

Input parameters:

- `enabled` (boolean, required)
- `profile` (string)
- `project` (string, required)

### `gflow_instructions_apply` (~84 tokens)

Declaratively FULL-SYNC a Flow project's brief: REPLACES all existing instruction cards with the given set (destructive — cards not listed are removed). Each card is {'title', 'text', 'ref': [...], 'enabled'}. Credits-free.

Input parameters:

- `cards` (array, required)
- `profile` (string)
- `project` (string, required)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/ffroliva-gflow-cli/gflow-cli#diagnostics

## Score history

- 2026-09-20: 68
- 2026-09-19: 67
- 2026-09-18: 52
- 2026-09-17: 66
- 2026-09-16: 66

## Common questions

### What is the gflow-cli MCP server?

gflow-cli is an MCP server listed in the public MCP registry as io.github.ffroliva/gflow-cli. Drive Google Flow from an agent: Veo video and Imagen image generation. This page covers its PyPI package (gflow-cli).

### Is the gflow-cli MCP server safe to use?

gflow-cli scores 68 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. 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 gflow-cli MCP server expose?

gflow-cli exposes 16 tools: gflow_generate_image, gflow_generate_video, gflow_list_tools, gflow_get_credits, gflow_character_list, and 11 more. Their descriptions and schemas cost roughly 1,634 tokens of context every time the server is loaded.

### Is the gflow-cli MCP server still maintained?

gflow-cli is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- PyPI project: https://pypi.org/project/gflow-cli/
- Socket report: https://socket.dev/pypi/package/gflow-cli
- Repository: https://github.com/ffroliva/gflow-cli
- Website: https://ffroliva.github.io/gflow-cli/
- Changelog RSS feed: https://verifymcp.io/servers/ffroliva-gflow-cli/gflow-cli.xml
- Changelog JSON feed: https://verifymcp.io/servers/ffroliva-gflow-cli/gflow-cli.json
- HTML version of this page: https://verifymcp.io/servers/ffroliva-gflow-cli/gflow-cli