Provides image recognition by routing images to any OpenAI-compatible vision model, enabling analysis of local files, URLs, or clipboard images with models like GPT-4o, GLM-4V, and Qwen-VL.
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., "@claude-image-recognition-mcp Describe this image: /tmp/screenshot.png"
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.
OpenAI-compatible vision recognition MCP server. Lets any MCP client (Claude Code with a non-multimodal model, etc.) "see" images by routing them to any OpenAI-compatible vision model (GLM-4V, Qwen-VL, GPT-4o, vLLM, …).
npm i claude-image-recognition-mcp
# or use directly via npx
npx claude-image-recognition-mcpRelated MCP server: z_ai_vision_mcp_server_clone
Set environment variables (all prefixed IMAGE_RECOGNITION_):
Var | Required | Default | Description |
| ✅ | — | API key |
| ✅ | — | OpenAI-compatible root, e.g. |
| ✅ | — | Vision model id, e.g. |
| ❌ |
|
|
| ❌ |
| 64–8192 |
| ❌ |
| per-request timeout |
| ❌ |
|
|
| ❌ |
| local file size cap |
{
"mcpServers": {
"image-recognition": {
"type": "stdio",
"command": "npx",
"args": ["-y", "claude-image-recognition-mcp"],
"env": {
"IMAGE_RECOGNITION_API_KEY": "<key>",
"IMAGE_RECOGNITION_BASE_URL": "https://open.bigmodel.cn/api/paas/v4",
"IMAGE_RECOGNITION_MODEL": "glm-4v-plus"
}
}
}
}recognize_imageParam | Type | Description |
| string (required) | local path / http(s) URL / literal |
| string | question or instruction (default: describe the image) |
| string? | override configured model id |
|
| OpenAI vision detail |
| number? | 64–8192 |
Windows: Win+Shift+S, then pass image: "clipboard"
macOS: needs brew install pngpaste
Linux: needs wl-paste (Wayland) or xclip (X11)
MIT
Recognize / analyze an image via an OpenAI-compatible vision model. Supports a local file path, an http(s) URL, or the literal 'clipboard'. Returns the model's textual answer to your prompt.
| Name | Required | Description | Default |
|---|---|---|---|
| image | Yes | Local file path | http(s) URL | the literal 'clipboard' | |
| model | No | Override the configured vision model id | |
| detail | No | OpenAI vision detail level (default: high) | |
| prompt | No | Question or instruction about the image | Describe this image in detail. |
| max_tokens | No | Max tokens for the response |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the transparency burden. It discloses that the tool uses an OpenAI-compatible vision model and returns a textual answer, implying an external network call. However, it does not mention error behavior, side effects, or privacy implications of sending images to a remote model, which would be relevant for a tool like this.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the action, and every sentence conveys necessary information without any fluff. It is a model of concise, effective tool definition.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has 5 parameters and no output schema, but the description explains the core purpose, accepted image sources, and return type. It does not describe the other parameters in detail, but the schema does, and for a moderately complex tool this is adequate and slightly above average.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The description primarily restates the image parameter's allowed formats (local path, URL, clipboard), which adds minimal value over the schema. It does not elaborate on the other parameters beyond what the schema already provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb 'Recognize / analyze' plus resource 'an image', and clearly states the supported input formats and return type. It unambiguously identifies the tool as an image analysis tool, even though no sibling tools exist to distinguish from.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no explicit when-to-use vs alternatives, but since no sibling tools are provided, the context is clear. The description implies its use for analyzing images via a vision model and lists accepted input sources, giving sufficient guidance for when to choose this tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0recognize_imageScored across 1 tool
With only a single tool, there is no possibility of confusion between tools; the tool's name and description clearly define its purpose.
The tool name follows a clear verb_noun convention (recognize_image), and since there is only one tool, naming consistency is trivially maintained.
The server exposes a single tool, which is on the edge of being too few for a typical MCP server. While the tool is substantive and not trivial, the surface area feels thin compared to servers that offer multiple related operations.
The tool covers the core operation of image recognition/analysis with flexible input sources (path, URL, clipboard). Minor gaps might include additional controls or metadata, but the primary workflow is well-covered.
Focused MCP server for OpenAI image/audio generation (v2.0.0). Wraps endpoints via HAPI CLI.
MCP server for Qwen Image 3 AI image generation
OCR, transcription, file extraction, and image generation for AI agents via MCP.
MCP server for Google Veo AI video generation