llm-vision-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@llm-vision-mcp diagnose this error screenshot"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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 understandingextract_text_from_image: OCR for screenshots, logs, documents, code, and UI textdiagnose_error_screenshot: error screenshot and stack trace diagnosisunderstand_technical_diagram: architecture, flowchart, UML, ER, sequence, and network diagramsanalyze_data_visualization: charts, tables, dashboards, and metrics screenshotsui_to_artifact: UI screenshot to implementation notes or design specsui_diff_check: expected vs actual UI screenshot comparison
Related MCP server: llm-vision-mcp
Setup
npm install
cp .env.example .envSet 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_keyOptional:
# 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=120000Step Plan
Step Plan uses the same API key style but a different Base URL:
STEPFUN_API_MODE=step_planWhen 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-flashYou 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-flashFor 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 startRun With npx
After this package is published to npm:
npx -y llm-vision-mcpThe 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://pathhttp://orhttps://URLdata: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 toolsanalyze_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
Scored across 7 tools
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.
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.
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.
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
Related MCP Connectors
MCP server for AI dialogue using various LLM models via AceDataCloud
MCP server for OpenAI API (chat completions, image generation, embeddings) via AceDataCloud
MCP server for Qwen Image 3 AI image generation
Hosted Screenshots MCP server for Claude, ChatGPT and Cursor, with each action switched per account.
Related MCP Servers
- AlicenseBqualityDmaintenanceA TypeScript-based MCP server that enables text-to-image generation using Cloudflare's Flux Schnell model API.15MIT
- AlicenseNot gradedqualityDmaintenanceAn MCP server that enables any LLM to describe images from file paths, URLs, or base64 data by forwarding them to a supported vision provider such as OpenAI, Anthropic, or local Ollama models.378 npm10MIT
- AlicenseNot gradedqualityCmaintenanceA local MCP server that gives LLMs eyes for images by performing object detection (YOLOv8) and text recognition (EasyOCR), outputting descriptive statements about objects and text positions without any API key or cloud dependency.MIT
- AlicenseAqualityDmaintenanceA local MCP server that gives vision to vision-less LLMs by describing images and extracting text via Alibaba DashScope vision models.2MIT