Skip to main content
Glama
wonderstone843

Vision QA MCP

by wonderstone843
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Vision QA MCP

An MCP server that gives an AI agent automated quality control for generated images. After a model produces an image, the agent calls qa_check and gets back a structured verdict — character accuracy, style consistency, quality, and composition, scored against your reference images and rules — powered by Claude vision.

Built for AI media pipelines where a human can't eyeball every frame: generate → QA → regenerate-if-failed, automatically.

Why

Image models drift. A character loses a feature, the style wobbles, a hand comes out wrong. In a production pipeline that ships dozens of images, you need the agent itself to catch this before a human ever sees it. This server makes "QA every image" a single tool call with a pass/fail and actionable issues — and it pairs naturally with claude-vision-mcp (let the agent see) for a full see-and-verify loop.

Related MCP server: image-forensics-mcp

Tools

  • qa_check — review one image and return a structured verdict:

    • passed (bool), overall_score, and per-axis scores (character_accuracy, style_consistency, quality_score, composition_score) on a 0–1 scale

    • issues — a list of {severity, category, description, recommendation} (severity: critical / warning / minor)

    • should_regenerate (bool) and a one-line notes summary

    • Fails automatically on any critical issue, regardless of score.

  • list_scene_types — the supported scene_type values and what each expects.

You pass your own rules and references, so it works for any project:

qa_check(
  image_path="/path/to/generated.png",
  reference_images=["/refs/hero_front.png", "/refs/hero_face.png"],
  character_rules="The pilot has NO eyebrows in this form. Jacket has horizontal stripes, not clouds.",
  style_notes="High-contrast anime cel shading, cosmic purple lighting.",
  scene_type="solo",          # solo | portrait | battle | combat | group | action | interview
  pass_threshold=0.7,
)

scene_type adjusts composition expectations — e.g. a portrait may face the camera, while battle characters should face each other.

Requirements

  • Python ≥ 3.10

  • An Anthropic API key (ANTHROPIC_API_KEY)

  • Dependencies: mcp[cli], anthropic, Pillow

Install

git clone https://github.com/wonderstone843/vision-qa-mcp.git
cd vision-qa-mcp
pip install -e .
export ANTHROPIC_API_KEY=sk-ant-...

Use with Claude Code

claude mcp add vision-qa -- vision-qa-mcp

Or add to your MCP config:

{
  "mcpServers": {
    "vision-qa": { "command": "vision-qa-mcp" }
  }
}

Then instruct your agent: "After generating each image, run qa_check against the character refs; regenerate any that don't pass."

Configuration

  • ANTHROPIC_API_KEY (required)

  • ANTHROPIC_MODEL (optional, default claude-opus-4-8) — for QA on every generation, claude-haiku-4-5 or claude-sonnet-4-6 are cheaper and usually sufficient.

How it works

The image is downscaled to stay under the vision API limits, sent to Claude alongside any reference images and your rules, and the model is forced to call a submit_qa tool whose schema defines the four scores plus the issues list — so the output is always structured and parseable. The pass decision is overall_score >= pass_threshold AND no critical issues.

vision_qa_mcp/
  server.py   FastMCP server: qa_check + list_scene_types
  review.py   prompt, scoring rubric, forced-tool call to Claude vision
  images.py   downscale + base64-encode for the vision API

License

MIT — see LICENSE. Author: Joshua Penn.

Available Tools

2 tools
list_scene_typesA

List the supported scene_type values and what each one expects.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

A4.2/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It correctly indicates a read-only listing operation, which is adequate for a simple query tool. No side effects are expected, and the description adequately covers the behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, concise sentence that immediately communicates the tool's purpose with no extraneous words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, the description hints at the return format (values and expectations), which is mostly sufficient for a simple list. However, it lacks explicit structure details like whether it returns a list or map.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There are no parameters, so the baseline is 4. The description adds value by specifying the result will include both values and their expectations, which goes beyond the empty input schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'list' and the resource 'supported scene_type values', and adds the detail 'and what each one expects', providing a specific purpose that distinguishes it from the sibling tool 'qa_check'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for retrieving scene type options but provides no explicit guidance on when to use this tool versus alternatives, nor any exclusions or prerequisites.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

qa_checkA

Run a quality-control check on a generated image and return a structured verdict.

Call this immediately after generating an image, before showing it to the user.

Parameters:

  • image_path: Absolute path to the generated image to review.

  • reference_images: Optional list of reference image paths to compare against (e.g. character/style references). Up to 3 are used.

  • character_rules: Free-text rules the image must follow, e.g. "The pilot has NO eyebrows; the jacket has horizontal stripes."

  • style_notes: Free-text description of the expected visual style.

  • scene_type: One of solo, portrait, battle, combat, group, action, interview. Adjusts composition expectations (e.g. portraits may face camera).

  • pass_threshold: Minimum overall score (0-1) to pass. Default 0.7.

Returns a dict with: passed (bool), overall_score, character_accuracy, style_consistency, quality_score, composition_score (all 0-1), issues (list of {severity, category, description, recommendation}), should_regenerate (bool), notes, and model.

ParametersJSON Schema
NameRequiredDescriptionDefault
image_pathYes
scene_typeNogroup
style_notesNo
pass_thresholdNo
character_rulesNo
reference_imagesNo

TDQS

A4.1/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It explains the return value structure and parameter behavior (e.g., reference_images limited to 3), but does not disclose possible side effects, error handling, or auth requirements. It is adequate but not fully transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is moderately long but well-structured, with a clear purpose statement followed by parameter details. It is front-loaded with the core action. Minor redundancy could be trimmed, but overall it is efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 6 parameters, no output schema, and no annotations, the description covers the return dict fields and parameter defaults. However, it lacks information about validation rules, error handling, and the allowed enum values for scene_type (though a sibling tool exists). It is somewhat incomplete for a complex tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description thoroughly explains all 6 parameters, including types, defaults, and usage examples (e.g., character_rules example, scene_type with composition expectations). This adds significant meaning beyond the bare schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Run a quality-control check on a generated image and return a structured verdict' and specifies when to call it ('immediately after generating an image, before showing it to the user'). This provides a specific verb+resource and distinguishes it from the sibling tool 'list_scene_types'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly advises 'Call this immediately after generating an image, before showing it to the user,' which is clear usage guidance. However, it does not explicitly state when not to use the tool or mention alternatives, so it loses one point.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 2 tool updatesv0.1.0
    • First observedlist_scene_types
    • First observedqa_check
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.1/5.0

Scored across 2 tools

Disambiguation5/5

The two tools have completely distinct purposes: one lists scene types and their expectations, the other performs a quality check on images. There is no overlap or ambiguity.

Naming Consistency4/5

Both tools use snake_case, but one follows a verb_noun pattern (list_scene_types) while the other uses an abbreviated prefix (qa_check). The pattern is mostly consistent but has a minor deviation.

Tool Count3/5

With only 2 tools, the server is very focused. While it covers its core purpose, the count is on the low end and may feel thin for some use cases.

Completeness3/5

The tool set provides the essential functions: listing scene types and running a QA check. However, there is no tool to inspect or manage scene types beyond listing, and no tool to modify thresholds or references, leaving minor gaps.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • imagefeatures-mcp

    kelkalot
    A
    license
    A
    quality
    D
    maintenance
    An MCP server that provides classic computer vision feature extraction tools (color, texture, shape) for image analysis, enabling LLMs to perform precise mathematical image comparisons and quality assessments.
    9
    MIT

  • imgx-mcp

    somacoffeekyoto
    A
    license
    Not graded
    quality
    C
    maintenance
    An MCP server for AI image generation and editing, allowing users to generate images from text, edit existing images with instructions, and manage iterative editing sessions with undo/redo.
    41 npm
    MIT

  • aifmt

    ericchansen
    A
    license
    Not graded
    quality
    D
    maintenance
    An MCP server that fixes, validates, and generates visual text content for AI coding assistants.
    MIT