# Local GPU Imagegen (pypi · local-gpu-imagegen)

MCP-first control plane for ComfyUI workflows with explicit approvals and no silent downloads.

- Trust score: 65/100 (medium)
- Change this week: +19
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-21

## Components

- pypi · `local-gpu-imagegen`: 65/100 (this document), [markdown](https://verifymcp.io/servers/chevalgrand520-local-gpu-imagegen/local-gpu-imagegen.md), [page](https://verifymcp.io/servers/chevalgrand520-local-gpu-imagegen/local-gpu-imagegen)

## Channel facts

- Registry: `pypi`
- Package: `local-gpu-imagegen`
- Version: `0.9.1`
- 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 2026-09-21.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Install-script risk not yet assessed.
  - 2 of 13 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: no license is declared.
  - Actively maintained (last published 21 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 58/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 1622 tokens (~95/item across 17 items; 17 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 70/100
  - Stability observed for 21 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 74/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 8% 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 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "local_gpu_finalize_run" implies "publish" 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**: 20/100
  - Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28.

## Install

### How do I install the Local GPU Imagegen MCP server?

Local GPU Imagegen runs locally as a PyPI package, launched with uvx local-gpu-imagegen. 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 chevalgrand520-local-gpu-imagegen -- uvx local-gpu-imagegen
```

### Cursor

```json
{
  "mcpServers": {
    "chevalgrand520-local-gpu-imagegen": {
      "command": "uvx",
      "args": [
        "local-gpu-imagegen"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "chevalgrand520-local-gpu-imagegen": {
      "command": "uvx",
      "args": [
        "local-gpu-imagegen"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add chevalgrand520-local-gpu-imagegen -- uvx local-gpu-imagegen
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "chevalgrand520-local-gpu-imagegen": {
      "type": "local",
      "command": [
        "uvx",
        "local-gpu-imagegen"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add chevalgrand520-local-gpu-imagegen --command uvx --arg local-gpu-imagegen
```

### Hermes

```yaml
mcp_servers:
  chevalgrand520-local-gpu-imagegen:
    command: "uvx"
    args: ["local-gpu-imagegen"]
```

### Netclaw

```json
{
  "McpServers": {
    "chevalgrand520-local-gpu-imagegen": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "local-gpu-imagegen"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add chevalgrand520-local-gpu-imagegen -t stdio -c uvx -a local-gpu-imagegen
```

### Other

```json
{
  "mcpServers": {
    "chevalgrand520-local-gpu-imagegen": {
      "command": "uvx",
      "args": [
        "local-gpu-imagegen"
      ]
    }
  }
}
```

## 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.

### 2026-09-21 (score 65, +1)

No change was recorded against any check on this day. Stability & Change Management went from 67 to 70. That category is still filling its 30-day observation window: 20 days of observed history at the previous scan, 21 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-19 (score 64, +1)

No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-17 (score 63, +1)

No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-15 (score 62, +16)

- [security improvement] Malware scan: unverified → pass

### 2026-09-14 (score 46, −15)

- [security regression] Malware scan: pass → unverified

### 2026-09-13 (score 61, +1)

No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-12 (score 60, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-09-11 (score 45, −14)

- [security regression] Malware scan: pass → unverified

## MCP tools (17)

### `local_gpu_imagegen_check` (~23 tokens)

Check Python packages and CUDA readiness for local GPU image generation.

Output parameters:

- `bootstrap` (object)
- `diffusers_ready` (boolean)
- `ready` (boolean)
- `webui_ready` (boolean)

### `local_gpu_generate_image` (~235 tokens)

Compatibility tool for WebUI or Diffusers image generation; not for ComfyUI routes and never a bypass for the confirmed high-level run workflow.

Input parameters:

- `allow_cpu` (boolean)
- `allow_download` (boolean)
- `backend` (string)
- `cpu_offload` (boolean)
- `disable_safety_checker` (boolean)
- `filename` (string)
- `guidance_scale` (number)
- `height` (integer)
- `input_image` (string)
- `lora` (array)
- `lora_scale` (number)
- `mask_image` (string)
- `mode` (string)
- `model` (string)
- `negative_prompt` (string)
- `output_dir` (string)
- `prompt` (string, required)
- `sampler_name` (string)
- `scheduler` (string)
- `seed` (integer)
- `steps` (integer)
- `strength` (number)
- `vae_tiling` (boolean)
- `webui_url` (string)
- `width` (integer)

Output parameters:

- `backend` (string)
- `mode` (string)
- `ok` (boolean)
- `path` (string)

### `local_gpu_discover_models` (~143 tokens)

Plan or execute bounded local model discovery without loading model weights.

Input parameters:

- `authorization_id` (string)
- `backends` (array)
- `confirmation` (string): Exact confirmation token returned by the matching discovery plan; required before filesystem access.
- `expected_backend_model_id` (string)
- `explicit_includes` (array)
- `mode` (string)
- `network_confirmation` (string): Exact separately displayed confirmation authorizing network verification for this unchanged plan.
- `phase` (string, required)
- `plan_id` (string)
- `roots` (array)
- `selected_candidates` (array)
- `stage` (string)

### `local_gpu_inspect_workflow` (~41 tokens)

Inspect one local ComfyUI API workflow and infer a safe ordinary txt2img binding without writing state.

Input parameters:

- `workflow_path` (string, required)

### `local_gpu_register_workflow` (~51 tokens)

Recheck and immutably register one exact previously inspected ComfyUI workflow proposal.

Input parameters:

- `confirmation` (string, required)
- `proposal_digest` (string, required)
- `workflow_path` (string, required)

### `local_gpu_set_model_trust` (~196 tokens)

Inspect, approve, or revoke one exact current local model identity. A trust mutation requires the exact confirmation previously returned for the same mutation boundary, displayed to the user, and repeated in a later user message.

Input parameters:

- `action` (string, required): Trust operation to inspect, approve, or revoke for the exact supplied identity.
- `capabilities` (object)
- `catalog_id` (string)
- `component_identity_tokens` (array)
- `confirmation` (string): Exact confirmation string returned for this mutation and repeated in a later user message.
- `identity_token` (string, required): Exact model identity token returned by discovery or workflow inspection.
- `preference` (integer)
- `public_metadata` (object)
- `registered_workflow_id` (string)
- `two_stage_layout` (object)
- `workflow_binding` (object)
- `workflow_path` (string)
- `workflow_template_id` (string)

### `local_gpu_recommend_models` (~168 tokens)

Recommend one exact confirmed-capability route and at most two alternatives. preferred_model_id must be an exact catalog ID. Requires prior api_only discovery and model trust (local_gpu_discover_models then local_gpu_set_model_trust). Display the selected route and start_run_boundary, then wait for later user confirmation before local_gpu_start_run.

Input parameters:

- `affinity_tags` (array, required)
- `authorization_scope` (string, required)
- `height` (integer, required)
- `operation` (string, required)
- `preferred_model_id` (string|null, required)
- `profile` (string, required)
- `regional_layout` (object)
- `required_vram_gb` (number|null, required)
- `style` (string|null, required)
- `two_stage_layout` (object)
- `width` (integer, required)

### `local_gpu_list_profiles` (~30 tokens)

List registered visual-asset profiles and current local backend capabilities.

Input parameters:

- `authorization_scope` (string)

### `local_gpu_start_run` (~162 tokens)

Create a visual-asset run only after later user confirmation; copy start_run_boundary exactly from the previously displayed recommendation and add the remaining run fields.

Input parameters:

- `authorization_scope` (string, required)
- `backend` (string, required)
- `constraints` (object, required)
- `initial_regional_conditioning` (object)
- `initial_two_stage_conditioning` (object)
- `intent` (string, required)
- `max_rounds` (integer, required)
- `model_choice` (string, required)
- `profile` (string, required)
- `route_token` (string, required): Opaque recommendation token binding the model, workflow, backend, dimensions, and authorization scope.
- `style` (string|null, required)
- `subtype` (string, required)
- `upscale_policy` (string, required)

### `local_gpu_get_run` (~30 tokens)

Get the current persisted state of a visual-asset run.

Input parameters:

- `run_id` (string, required)

### `local_gpu_branch_run` (~73 tokens)

Create an immutable child revision run from one reviewed parent round.

Input parameters:

- `contract` (object, required)
- `denoising_strength` (number)
- `edit_mode` (string, required)
- `max_rounds` (integer, required)
- `parent_round` (integer, required)
- `parent_run_id` (string, required)

### `local_gpu_prepare_mask` (~57 tokens)

Prepare an unconfirmed child-run inpaint mask and return its JPEG overlay.

Input parameters:

- `feather_pixels` (integer)
- `geometry` (array)
- `run_id` (string, required)
- `user_mask_path` (string)

### `local_gpu_confirm_mask` (~36 tokens)

Confirm an unchanged prepared mask after explicit overlay approval.

Input parameters:

- `mask_id` (string, required)
- `run_id` (string, required)

### `local_gpu_generate_round` (~138 tokens)

Generate one root or immutable revision round and return an optional bounded JPEG preview. Construct the plan from the frozen run returned by local_gpu_get_run, copying every confirmed route, identity, workflow, compiler, policy, and budget field.

Input parameters:

- `action` (string, required)
- `change_summary` (string, required)
- `edit_mode` (string, required)
- `idempotency_key` (string, required): Caller-chosen key for safely retrying the same round request; reuse with different inputs is rejected.
- `mask_id` (string)
- `plan` (object, required)
- `run_id` (string, required)
- `seed` (integer, required)

### `local_gpu_record_review` (~100 tokens)

Record human or model review evidence for one generated round.

Input parameters:

- `constraint_results` (object, required)
- `critique` (string, required)
- `hard_failures` (array, required)
- `next_action` (string, required)
- `preservation_results` (array)
- `round_number` (integer, required)
- `run_id` (string, required)
- `scores` (object, required)
- `stage_checks` (object)
- `visual_checks` (object, required)

### `local_gpu_finalize_run` (~81 tokens)

Publish the selected reviewed round as the run's final PNG.

Input parameters:

- `confirmation` (string, required): Exact finalize:<run_id>:<round_number>:<image_sha256> value previously displayed to the user.
- `postprocess` (object)
- `round_number` (integer, required)
- `run_id` (string, required)
- `summary` (string, required)

### `local_gpu_cleanup_run` (~58 tokens)

Remove run intermediates or a fully confirmed run directory.

Input parameters:

- `confirmation` (string, required): Exact run_id required to authorize cleanup; scope all removes the complete run directory.
- `run_id` (string, required)
- `scope` (string, required)

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/chevalgrand520-local-gpu-imagegen/local-gpu-imagegen#diagnostics

## Score history

- 2026-09-21: 65
- 2026-09-20: 64
- 2026-09-19: 64
- 2026-09-18: 63
- 2026-09-17: 63
- 2026-09-16: 62
- 2026-09-15: 62
- 2026-09-14: 46
- 2026-09-13: 61
- 2026-09-12: 60
- 2026-09-11: 45
- 2026-09-10: 59
- 2026-09-09: 59
- 2026-09-08: 59
- 2026-09-07: 58
- 2026-09-06: 55
- 2026-09-05: 55
- 2026-09-04: 55
- 2026-09-03: 55
- 2026-09-02: 55
- 2026-09-01: 55
- 2026-08-31: 55

## Common questions

### What is the Local GPU Imagegen MCP server?

Local GPU Imagegen is an MCP server listed in the public MCP registry as io.github.ChevalGrand520/local-gpu-imagegen. MCP-first control plane for ComfyUI workflows with explicit approvals and no silent downloads. This page covers its PyPI package (local-gpu-imagegen).

### Is the Local GPU Imagegen MCP server safe to use?

Local GPU Imagegen scores 65 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 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 Local GPU Imagegen MCP server expose?

Local GPU Imagegen exposes 17 tools: local_gpu_imagegen_check, local_gpu_generate_image, local_gpu_discover_models, local_gpu_inspect_workflow, local_gpu_register_workflow, and 12 more. Their descriptions and schemas cost roughly 1,622 tokens of context every time the server is loaded.

### Is the Local GPU Imagegen MCP server still maintained?

Local GPU Imagegen is still listed as active in the MCP registry. We last reached this channel on 21 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/local-gpu-imagegen/
- Socket report: https://socket.dev/pypi/package/local-gpu-imagegen
- Repository: https://github.com/ChevalGrand520/local-gpu-imagegen
- Changelog RSS feed: https://verifymcp.io/servers/chevalgrand520-local-gpu-imagegen/local-gpu-imagegen.xml
- Changelog JSON feed: https://verifymcp.io/servers/chevalgrand520-local-gpu-imagegen/local-gpu-imagegen.json
- HTML version of this page: https://verifymcp.io/servers/chevalgrand520-local-gpu-imagegen/local-gpu-imagegen