# us.limner/limner (mcpb · limner-mcp.mcpb)

AI visual generation agent: multi-pipeline rendering, prompt crafting, and image composition.

- Trust score: 43/100 (low)
- Change this week: +2
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `mcp.limner.us`: 31/100, [markdown](https://verifymcp.io/servers/us-limner-limner/mcp.md), [page](https://verifymcp.io/servers/us-limner-limner/mcp)
- mcpb · `limner-mcp.mcpb`: 43/100 (this document), [markdown](https://verifymcp.io/servers/us-limner-limner/https-github-com-vinsonconsulting-limner-releases-download-mcpb-v1-0-1-limner-mc.md), [page](https://verifymcp.io/servers/us-limner-limner/https-github-com-vinsonconsulting-limner-releases-download-mcpb-v1-0-1-limner-mc)

## Channel facts

- Registry: `mcpb`
- Package: `https://github.com/vinsonconsulting/limner/releases/download/mcpb-v1.0.1/limner-mcp.mcpb`
- 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 2026-08-03.

- **Supply Chain Security**: 14/100
  - Malware scan not yet available for this package.
  - CVE data not yet available for this package.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (101 of 106), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 26 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 78/100
  - 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 1969 tokens (~93/item across 21 items; 18 tools + 3 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 90/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 70% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

- Download bundle: `https://github.com/vinsonconsulting/limner/releases/download/mcpb-v1.0.1/limner-mcp.mcpb`

## 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.

### 2026-08-02 (score 43, +29)

- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional regression] Dependency health: partial → unverified
- [functional regression] Security disclosure: fail → unverified
- [functional improvement] Schema quality: unverified → good
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Schema quality: unverified → 100

### 2026-08-01 (score 14, −23)

- [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] Schema quality: 100 → unverified
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass

### 2026-07-31 (score 37, −4)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 41, −2)

- [functional regression] Maintenance: pass → unverified

### 2026-07-28 (score 43, +2)

- [functional improvement] Maintenance: unverified → pass

### 2026-07-27 (score 41)

First indexed and scored.

## MCP tools (18)

### `limner_generate_dalle` (~223 tokens)

Generate or edit an image via OpenAI Images API (gpt-image-1 default; pass `image` to restyle a source). Paid API — each call bills your OpenAI account.

Input parameters:

- `background` (string): transparent requires outputFormat png/webp.
- `image` (string): Source image URL for a likeness-preserving edit/restyle (gpt-image-1 image-edits). Pass a fetchable URL — e.g. an artifact URL from a prior generate — not inline base64.
- `model` (string): OpenAI gpt-image model id. Defaults to gpt-image-1.
- `outputFormat` (string): Output image format. Defaults to png server-side.
- `prompt` (string, required)
- `quality` (string): Detail vs. cost/latency: low|medium|high|auto. Sent only when set.
- `size` (string): Output size, e.g. "1024x1024", "1024x1536", "1536x1024", or "auto".

### `limner_generate_midjourney` (~227 tokens)

Compose a Midjourney prompt string (prompt-only; no image generation; downstream tool runs the HITL step). Supports image-prompt + --sref/--oref reference URLs.

Input parameters:

- `aspectRatio` (string): e.g. "16:9", "1:1", "9:16"
- `chaos` (integer)
- `image` (string): Image-prompt URL, composed at the start of the prompt. Use a fetchable URL.
- `imageWeight` (number): Midjourney --iw image weight, 0-3 (default 1). Applies to `image`.
- `modelVersion` (string): e.g. "6", "7"
- `omniRef` (string): Omni-reference URL (v7 subject/character consistency) → --oref.
- `prompt` (string, required)
- `seed` (integer)
- `styleRef` (string): Style-reference URL → --sref.
- `stylize` (integer): Midjourney --stylize value, 0-1000. Default 100.

### `limner_generate_recraft` (~201 tokens)

Generate or restyle an image via Recraft's REST API (external.api.recraft.ai; pass `image` for image-to-image). Paid API — each call bills your Recraft account.

Input parameters:

- `image` (string): Source image URL for image-to-image. Pass a fetchable URL, not inline base64.
- `model` (string): e.g. "recraftv3", "recraftv2".
- `prompt` (string, required)
- `size` (string): e.g. "1024x1024", "1365x1024", "1024x1365".
- `strength` (number): Image-to-image strength 0-1 (lower = closer to the source). Default 0.5. Used only with `image`.
- `style` (string): e.g. "realistic_image", "digital_illustration", "vector_illustration".
- `substyle` (string)

### `limner_upscale` (~104 tokens)

Upscale a raster image (crisp: sharpen + enlarge toward print scale) via Recraft's REST API. Returns a larger raster image (PNG or WebP, depending on what the endpoint returns; the output mime reflects the actual bytes). Paid API — each call bills your Recraft account.

Input parameters:

- `image` (string, required): Source image URL to upscale. Pass a fetchable URL (e.g. an artifact URL from a prior generate), not inline base64.

### `limner_vectorize` (~77 tokens)

Vectorize a raster image into a scalable SVG via Recraft's REST API. Returns an SVG. Paid API — each call bills your Recraft account.

Input parameters:

- `image` (string, required): Source raster image URL to vectorize. Pass a fetchable URL (e.g. an artifact URL from a prior generate), not inline base64.

### `limner_compose` (~480 tokens)

Hybrid V8 composition stack. Wraps photon-ops, jsquash-codecs, satori-text, and cf-images-transform behind a single op-discriminated input. Inputs/outputs are base64-encoded image bytes (PNG default). cf-images ops require the Workers transport (IMAGES binding).

Input parameters:

- `background` (string): cfBackgroundFill background color/spec.
- `base` (string): base64 base image. Used by: watermark, cfOverlay.
- `delta` (number): brightness delta.
- `factor` (number): contrast factor.
- `fit` (string): resize fit mode: cover (only supported mode).
- `fonts` (array): renderText: built-in fonts by id (optional; defaults to ibm-plex-sans).
- `format` (string): Used by: encode, decode (jpeg|png|webp|avif).
- `from`: convert source format.
- `height` (integer): Used by: resize, crop, renderText, cfSmartCrop, cfBackgroundFill.
- `input` (string): base64 image bytes. Used by: resize, crop, brightness, contrast, blur, sharpen, decode, convert, cfTransform, cfBlur, cfSmartCrop, cfBackgroundFill.
- `jsx`: renderText: JSX-shaped object literal { type, props }.
- `left` (integer): Used by: cfOverlay.
- `op` (string, required): Composition op. The required fields differ per op (see each field).
- `opts` (object): cfTransform: transform options (width/height/fit/blur/brightness/contrast/background).
- `outputFormat` (string): cfTransform output format.
- `overlay` (string): base64 overlay image. Used by: watermark, cfOverlay.
- `quality` (integer): encode/convert quality, 1-100.
- `radius` (number): Used by: blur, cfBlur.
- `raw` (object): encode: raw RGBA source.
- `to`: convert target format.
- `top` (integer): Used by: cfOverlay.
- `width` (integer): Used by: resize, crop, renderText, cfSmartCrop, cfBackgroundFill.
- `x` (integer): Used by: crop, watermark.
- `y` (integer): Used by: crop, watermark.

### `limner_recall` (~78 tokens)

List memory entries matching the given filters.

Input parameters:

- `category` (string)
- `limit` (integer)
- `offset` (integer)
- `q` (string): Substring match against memory.content.
- `since` (integer): Unix epoch (ms). Filter to entries created at/after.
- `until` (integer)

### `limner_record` (~66 tokens)

Persist a new memory entry. Returns the assigned id + timestamps.

Input parameters:

- `category` (string)
- `content` (string, required)
- `metadata` (object)
- `sourceId` (string): Idempotency key — re-recording with the same sourceId upserts.

### `limner_forget` (~37 tokens)

Delete a memory entry by id. Returns { deleted: boolean }.

Input parameters:

- `id` (string, required): Memory entry id (ULID).

### `limner_list_categories` (~19 tokens)

Return all memory categories with their entry counts.

### `limner_create_project` (~65 tokens)

Create a project so notes and context can be attached to it. Returns the new project (id + timestamps). Names are unique.

Input parameters:

- `description` (string)
- `metadata` (object)
- `name` (string, required): Unique project name (the human-facing key).

### `limner_list_projects` (~44 tokens)

Return projects matching the given filters.

Input parameters:

- `limit` (integer)
- `offset` (integer)
- `q` (string): Substring match against project.name.

### `limner_get_project_context` (~60 tokens)

Return a project plus its recent notes. Identify by projectId or name.

Input parameters:

- `name` (string)
- `noteLimit` (integer): Number of recent notes to include. Defaults to 10.
- `projectId` (string)

### `limner_record_project_note` (~49 tokens)

Append a note to a project. Returns the new note (id + timestamp).

Input parameters:

- `content` (string, required)
- `metadata` (object)
- `projectId` (string, required)

### `limner_health` (~20 tokens)

Server health snapshot — bindings flavor, timestamp, version.

### `limner_version` (~19 tokens)

Return the @limner/mcp server version.

### `limner_list_pipelines` (~34 tokens)

List the pipelines registered with this server. For each pipeline returns id, displayName, kind, and required secrets.

### `limner_pipeline_capabilities` (~67 tokens)

Describe a specific pipeline's capability surface. Returns kind + transport + required secrets + the input options shape (heuristic; not a strict zod export).

Input parameters:

- `id` (string, required): Pipeline id (e.g. "dalle", "midjourney", "recraft").

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/us-limner-limner/https-github-com-vinsonconsulting-limner-releases-download-mcpb-v1-0-1-limner-mc#diagnostics

## Score history

- 2026-08-03: 43
- 2026-08-02: 43
- 2026-08-01: 14
- 2026-07-31: 37
- 2026-07-30: 41
- 2026-07-28: 43
- 2026-07-27: 41

## Links

- Repository: https://github.com/vinsonconsulting/limner
- Changelog RSS feed: https://verifymcp.io/servers/us-limner-limner/https-github-com-vinsonconsulting-limner-releases-download-mcpb-v1-0-1-limner-mc/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/us-limner-limner/https-github-com-vinsonconsulting-limner-releases-download-mcpb-v1-0-1-limner-mc/changelog.json
- HTML version of this page: https://verifymcp.io/servers/us-limner-limner/https-github-com-vinsonconsulting-limner-releases-download-mcpb-v1-0-1-limner-mc