z_ai_vision_mcp_server_clone
Provides tools for image analysis using OpenAI-compatible vision models. Allows AI agents to analyze images, extract text, diagnose screenshots, understand technical diagrams, analyze data visualizations, check UI differences, and convert UI to artifacts via any OpenAI-compatible vision API endpoint.
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., "@z_ai_vision_mcp_server_clone 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.
z_ai_vision_mcp_server_clone
OpenAI-compatible MCP server for running image analysis tools against your own vision model endpoint.
Tools
ui_to_artifactextract_text_from_screenshotdiagnose_error_screenshotunderstand_technical_diagramanalyze_data_visualizationui_diff_checkanalyze_image
Related MCP server: vision-mcp
Configuration
Set either VISION_ENDPOINT or VISION_BASE_URL.
Variable | Required | Description |
| Yes, unless | Full chat completions endpoint. |
| Yes, unless | Base URL; |
| Yes | Vision model name sent in the request body. |
| No | Bearer token. Omit for local endpoints that do not require auth. |
| No | Label for your provider. Defaults to |
| No | Local image size limit. Defaults to |
| No | Request timeout. Defaults to |
| No | Optional model temperature. |
| No | Optional model top_p. |
| No | Optional max_tokens. |
You can also place these values in a local .env file in the working directory where the server starts. Real environment variables override .env values.
Run
npm install
npm run build
VISION_ENDPOINT=http://localhost:11434/v1/chat/completions VISION_MODEL=llava npm startOr with .env:
npm startMCP Client Example
{
"mcpServers": {
"z-ai-vision-clone": {
"type": "stdio",
"command": "npx",
"args": ["-y", "z_ai_vision_mcp_server_clone"],
"env": {
"VISION_ENDPOINT": "https://your-provider.com/v1/chat/completions",
"VISION_MODEL": "your-vision-model",
"VISION_API_KEY": "your-api-key"
}
}
}
}Available Tools
7 toolsanalyze_data_visualizationAnalyze Data VisualizationC
Analyze charts, graphs, and dashboards for metrics, trends, anomalies, and implications.
Inputs: prompt (required), image_source (required), analysis_focus.
analyze_imageAnalyze ImageC
General-purpose image analysis for cases not covered by the specialized image tools.
Inputs: prompt (required), image_source (required).
diagnose_error_screenshotDiagnose Error ScreenshotC
Analyze an error screenshot and suggest likely causes and fixes.
Inputs: prompt (required), image_source (required), context.
extract_text_from_screenshotExtract Text from ScreenshotC
Extract visible text from a screenshot, including code, logs, terminal output, and documents.
Inputs: prompt (required), image_source (required), programming_language.
ui_diff_checkUI Diff CheckC
Compare a reference UI screenshot with an actual implementation screenshot.
Inputs: prompt (required), actual_image_source (required), expected_image_source (required).
ui_to_artifactUI to ArtifactC
Convert a UI screenshot into code guidance, a recreation prompt, a design spec, or a description.
Inputs: prompt (required), output_type (required), image_source (required).
understand_technical_diagramUnderstand Technical DiagramC
Explain architecture diagrams, flowcharts, UML, ER diagrams, and related technical drawings.
Inputs: prompt (required), image_source (required), diagram_type.
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 has a distinct purpose (e.g., data visualization vs. error screenshot vs. text extraction), but 'analyze_image' as a catch-all creates slight ambiguity since it overlaps with the specialized tools.
Most names follow a verb_noun pattern (analyze_*, extract_text_*, understand_*), but 'ui_diff_check' and 'ui_to_artifact' deviate slightly from the typical structure.
With 7 tools focused on image and UI analysis, the count is well-scoped—no unnecessary duplication and full coverage of the domain.
The tool set covers major visual analysis tasks (charts, screenshots, text extraction, UI comparison, diagram understanding) with no obvious gaps for the intended use case.
Maintenance
Related MCP Connectors
MCP server exposing the YourImageShare upload API (upload/list/delete) as tools for AI agents.
Focused MCP server for OpenAI image/audio generation (v2.0.0). Wraps endpoints via HAPI CLI.
MCP server for OpenAI API (chat completions, image generation, embeddings) via AceDataCloud
MCP server that lets AI assistants use all OneSchema features exposed via the public API.
Related MCP Servers
- AlicenseBqualityCmaintenanceA lightweight MCP server for image analysis using any OpenAI-compatible API endpoint, enabling AI agents to analyze images via a single tool.127 npmMIT
- AlicenseAqualityDmaintenanceMCP server that provides an analyze_image tool using OpenAI-compatible vision LLMs to describe images from file paths, URLs, or base64 data.115 npm1MIT
- FlicenseAqualityDmaintenanceOpenAI-compatible vision MCP server with 14 provider presets that enables MCP clients to analyze images, including screenshots, text, and UI mockups, via a single analyze_image tool.2-
- AlicenseNot gradedqualityDmaintenanceMCP server for analyzing images using multiple vision LLM providers (OpenCode, OpenAI, Anthropic, Google, and custom OpenAI-compatible endpoints). Provides tools to analyze single or multiple images, list providers, and test vision capabilities.MIT