Skip to main content
Glama

llm-vision-mcp

A TypeScript MCP server that gives text-only LLMs image understanding through StepFun vision models.

This is useful when the primary model, such as GLM5.2 or DeepSeek V4, does not support image input. The model can call these MCP tools, receive text or structured visual analysis, then continue reasoning with the result.

Tools

  • analyze_image: general image understanding

  • extract_text_from_image: OCR for screenshots, logs, documents, code, and UI text

  • diagnose_error_screenshot: error screenshot and stack trace diagnosis

  • understand_technical_diagram: architecture, flowchart, UML, ER, sequence, and network diagrams

  • analyze_data_visualization: charts, tables, dashboards, and metrics screenshots

  • ui_to_artifact: UI screenshot to implementation notes or design specs

  • ui_diff_check: expected vs actual UI screenshot comparison

Related MCP server: llm-vision-mcp

Setup

npm install
cp .env.example .env

Set STEPFUN_API_KEY in the MCP client environment. Injecting env vars through the MCP client config is usually the most explicit and reliable setup.

Required:

STEPFUN_API_KEY=your_stepfun_api_key

Optional:

# standard | step_plan
STEPFUN_API_MODE=standard
STEPFUN_BASE_URL=https://api.stepfun.com/v1
STEPFUN_VISION_MODEL=step-1o-turbo-vision
STEPFUN_DEFAULT_DETAIL=high
STEPFUN_TIMEOUT_MS=120000

Step Plan

Step Plan uses the same API key style but a different Base URL:

STEPFUN_API_MODE=step_plan

When STEPFUN_API_MODE=step_plan is set, defaults change to:

STEPFUN_BASE_URL=https://api.stepfun.com/step_plan/v1
STEPFUN_VISION_MODEL=step-3.7-flash

You can still override either value explicitly:

STEPFUN_API_MODE=step_plan
STEPFUN_BASE_URL=https://api.stepfun.com/step_plan/v1
STEPFUN_VISION_MODEL=step-3.7-flash

For backward compatibility, STEPFUN_USE_STEP_PLAN=true also enables Step Plan mode when STEPFUN_API_MODE is not set.

Run

npm run build
npm run start

Run With npx

After this package is published to npm:

npx -y llm-vision-mcp

The published package runs on Node.js and does not require Bun on the user's machine.

MCP Client Config

Example:

{
  "mcpServers": {
    "llm-vision-mcp": {
      "command": "node",
      "args": ["/Users/shaoyun/workdir/llm-vision-mcp/dist/index.js"],
      "env": {
        "STEPFUN_API_KEY": "your_stepfun_api_key",
        "STEPFUN_API_MODE": "step_plan",
        "STEPFUN_DEFAULT_DETAIL": "high"
      }
    }
  }
}

npm package example after publishing:

{
  "mcpServers": {
    "llm-vision-mcp": {
      "command": "npx",
      "args": ["-y", "llm-vision-mcp"],
      "env": {
        "STEPFUN_API_KEY": "your_stepfun_api_key",
        "STEPFUN_API_MODE": "step_plan",
        "STEPFUN_DEFAULT_DETAIL": "high"
      }
    }
  }
}

Image Inputs

Every single-image tool accepts:

{
  "image": "/absolute/path/to/screenshot.png",
  "question": "What does this error mean?",
  "detail": "high"
}

The image field supports:

  • local file path

  • file:// path

  • http:// or https:// URL

  • data:image/...;base64,... Data URL

ui_diff_check accepts two images:

{
  "expected_image": "/absolute/path/to/expected.png",
  "actual_image": "/absolute/path/to/actual.png",
  "question": "Focus on layout and missing buttons.",
  "detail": "high"
}

Notes

  • Use detail: "high" for OCR, UI, diagrams, charts, and screenshots.

  • Use detail: "low" for faster, cheaper coarse image understanding.

  • StepFun supports JPG/JPEG, PNG, WebP, and static GIF image inputs.

Available Tools

7 tools
analyze_data_visualizationAnalyze Data VisualizationB

Interpret charts, graphs, tables, dashboards, metrics screenshots, and data visualizations.

Inputs: image (required), model, detail, question, +1 more.

analyze_imageAnalyze ImageB

General-purpose image understanding for photos, screenshots, documents, objects, scenes, and visual questions.

Inputs: image (required), model, detail, question, +1 more.

diagnose_error_screenshotDiagnose Error ScreenshotB

Analyze error screenshots, stack traces, console output, IDE errors, terminal failures, and crash dialogs.

Inputs: image (required), model, detail, question, +1 more.

extract_text_from_imageExtract Text From ImageB

OCR for screenshots, documents, terminal output, logs, code snippets, forms, and UI text.

Inputs: image (required), model, detail, question, +1 more.

ui_diff_checkUI Diff CheckA

Compare expected and actual UI screenshots for visual regression, missing elements, layout differences, typography, color, spacing, and priority.

Inputs: actual_image (required), expected_image (required), model, detail, +2 more.

ui_to_artifactUI To ArtifactA

Convert UI screenshots into implementation notes, layout structure, design specs, or recreation prompts.

Inputs: image (required), model, detail, question, +1 more.

understand_technical_diagramUnderstand Technical DiagramB

Explain architecture diagrams, flowcharts, UML, sequence diagrams, ER diagrams, network diagrams, and system maps.

Inputs: image (required), model, detail, question, +1 more.

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    A3.8/5.0

    Scored across 7 tools

    Disambiguation5/5

    Each tool targets a distinct image understanding task: general analysis, OCR, error diagnosis, diagram explanation, data visualization, UI-to-code conversion, and UI diffing. The specialized scopes prevent confusion, even though analyze_image is broad, it serves as a catch-all rather than overlapping with specific tools.

    Naming Consistency4/5

    Most tools follow a verb-first naming pattern (analyze_image, extract_text_from_image, diagnose_error_screenshot, understand_technical_diagram, analyze_data_visualization), but two tools (ui_to_artifact, ui_diff_check) are noun-first. Despite this minor deviation, all names are readable and use consistent snake_case.

    Tool Count5/5

    With 7 tools, the server is well-scoped for image understanding. Each tool covers a distinct sub-domain (general analysis, OCR, errors, diagrams, data viz, UI artifacts, UI comparison), and no tool feels redundant or unnecessary.

    Completeness5/5

    The tool surface is comprehensive for an image understanding server, covering general understanding, text extraction, error diagnosis, diagram interpretation, data visualization analysis, UI-to-code conversion, and UI regression checking. There are no obvious missing operations within the stated domain.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers