agent-vision-mcp
Provides image analysis capabilities using OpenAI-compatible vision APIs, enabling AI agents to analyze and describe images.
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., "@agent-vision-mcp Analyze the image at /tmp/screenshot.png and describe what you see."
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.
agent-vision-mcp (hardened)
A hardened fork of @kitlau/agent-vision-mcp
— an MCP server that gives non-vision LLMs the ability to analyze images via any
OpenAI-compatible vision API (Claude Code, DeepSeek, etc.).
This build fixes intermittent empty / truncated image-analysis results and request hangs that affect long outputs (e.g. high-resolution 3D render screenshots) against self-hosted Qwen VLMs and similar backends.
What was broken upstream
The upstream package:
defaulted output
max_tokensto 1024 and never grew it, so long analyses hitfinish_reason: lengthand were cut off mid-sentence — and intermittently returned emptycontent, surfacing as❌ 视觉 API 返回的内容为空;only read
message.content, ignoringmessage.reasoning_contentused by Qwen3.x thinking-style models;had no retry on empty / 5xx / 429 / transient network errors;
set no client timeout, so slow high-res inference could hang and get killed (
MCP error -32001: user-cancel).
Related MCP server: image_mcp
What this build changes
dist/vision-client.js:
Grows
max_tokenson truncation (finish_reason === "length") and retries, so a low ceiling can never silently produce a partial/empty answer (grow ceiling: 32768).Falls back to
message.reasoning_contentwhencontentis empty (Qwen thinking mode).Retries on empty results, 5xx, 429, and network/timeout errors with exponential backoff (default 3 retries).
Sets an explicit client timeout (default 300000 ms) to prevent hangs.
dist/config.js:
Adds
VISION_MAX_TOKENS(default 16384),VISION_TIMEOUT_MS(default 300000),VISION_MAX_RETRIES(default 3) env vars, exposed on the config object.
Install as an MCP server
Point your MCP client at this repo. Example claude_desktop_config.json /
.mcp.json / global ~/.claude.json entry:
{
"mcpServers": {
"agent-vision": {
"type": "stdio",
"command": "node",
"args": ["path/to/this/repo/dist/index.js"]
}
}
}For a drop-in remote install, clone this repo and npm install, then run node dist/index.js.
Or add it as a dependency with npm install github:aabbccddwasd/agent-vision-mcp.
Environment variables
Variable | Default | Description |
| (required) | API key for the OpenAI-compatible endpoint |
|
| OpenAI-compatible base URL |
|
| The vision model, e.g. |
|
| Output token budget (was 1024 upstream) |
|
| Per-request client timeout |
|
| Retries for empty / 5xx / 429 / network errors |
|
| Optional disk response cache |
|
| Cache directory (when enabled) |
|
| Max image bytes (20 MB) |
License
MIT. Original author: kitlau86.
Available Tools
1 toolanalyze_imageAnalyze ImageARead-onlyIdempotent
Analyze an image with a vision AI model, giving a non-vision main model the ability to "see" image content. Call this when the user sends an image, or when you need to understand an image (describe it, OCR text, identify UI elements, read charts, etc.). The image can be provided as a base64 data URL, an HTTP(S) link, or a local file path.
Inputs: image (required), prompt (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
There is only one tool, so there is no possibility of ambiguity or misselection. The tool's purpose is clearly distinct and singular.
With a single tool named 'analyze_image', the naming follows a clear and consistent verb_noun pattern. There are no other tools to introduce inconsistency.
The server has only one tool, which is below the typical 3-15 range, but it is a narrow-purpose server focused on image analysis. The single tool is well-scoped and earns its place, making the count slightly under but reasonable.
The single tool covers a wide range of image analysis needs—description, OCR, UI element detection, chart reading, etc. There are no obvious gaps for the stated purpose of giving a non-vision model the ability to see.
Related MCP Connectors
Image & PDF tools for AI agents: compress, convert, resize, PDF, AI vision, pipeline.
Generate images with your own ChatGPT subscription (Plus, Pro or Team), without spending API credits
OCR, transcription, file extraction, and image generation for AI agents via MCP.
Run AI-powered analysis on images including moderation, captioning, tagging, and more.
Related MCP Servers
- AlicenseBqualityDmaintenanceEnables vision capabilities for any AI model by routing image analysis requests through OpenRouter's vision models. It provides tools to analyze images from URLs, local file paths, or base64 data.2630 npm19MIT
- AlicenseNot gradedqualityDmaintenanceEnables text-only LLMs to analyze images by routing them to an OpenAI-compatible vision backend, supporting local files, URLs, and data URLs.18 npmMIT
- FlicenseNot gradedqualityDmaintenanceEnables text-only language models to 'see' and describe images by calling multimodal APIs (OpenAI, Anthropic) for image analysis.-
- AlicenseAqualityDmaintenanceEnables LLMs to analyze images via OpenAI-compatible multimodal models, supporting local files, base64, and URLs with safety validation and model selection.1MIT