Skip to main content
Glama

mcp-openvision

by Nazruden
mcp_openvision_image_analysis.mcp.json5.15 kB
{ "description": "\n Analyze an image using OpenRouter's vision capabilities.\n\n This tool allows you to send an image to OpenRouter's vision models for analysis.\n You provide a query to guide the analysis and can optionally customize the system prompt\n for more control over the model's behavior.\n\n The query parameter is crucial for getting useful results. A well-crafted query should provide:\n 1. Purpose - Why you're analyzing this image\n 2. Focus areas - Specific elements or details to pay attention to\n 3. Required information - The type of information you need to extract\n 4. Format preferences - How you want the results structured\n\n Args:\n image: The image as a base64-encoded string, URL, or local file path\n query: A text prompt that guides the image analysis. For best results, provide context about\n why you're analyzing the image and what specific information you need.\n system_prompt: Optional instructions for the model defining its role and behavior\n model: The vision model to use (defaults to the value set by OPENROUTER_DEFAULT_MODEL)\n max_tokens: Maximum number of tokens in the response (100-4000)\n temperature: Temperature parameter for generation (0.0-1.0)\n top_p: Optional nucleus sampling parameter (0.0-1.0)\n presence_penalty: Optional penalty for new tokens based on presence in text so far (0.0-2.0)\n frequency_penalty: Optional penalty for new tokens based on frequency in text so far (0.0-2.0)\n project_root: Optional root directory to resolve relative image paths against\n\n Returns:\n The analysis result as text\n\n Examples:\n Basic usage with a file path:\n image_analysis(image=\"path/to/image.jpg\", query=\"Describe this image in detail\")\n\n Usage with a detailed contextual query:\n image_analysis(\n image=\"path/to/image.jpg\",\n query=\"Analyze this product packaging design for a fitness supplement. Identify all nutritional claims, certifications, and health icons. This is for a competitive analysis project.\"\n )\n\n Usage with custom system prompt:\n image_analysis(\n image=\"path/to/image.jpg\",\n query=\"What objects can you see in this image?\",\n system_prompt=\"You are an expert at identifying objects in images. Focus on listing all visible objects.\"\n )\n ", "name": "mcp_openvision_image_analysis", "parameters": { "properties": { "frequency_penalty": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "default": null, "title": "Frequency Penalty" }, "image": { "title": "Image", "type": "string" }, "max_tokens": { "default": 4000, "title": "Max Tokens", "type": "integer" }, "model": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "title": "Model" }, "presence_penalty": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "default": null, "title": "Presence Penalty" }, "project_root": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "title": "Project Root" }, "query": { "default": "Describe this image in detail", "title": "Query", "type": "string" }, "system_prompt": { "default": "You are an expert vision analyzer with exceptional attention to detail. Your purpose is to provide accurate, comprehensive descriptions of images that help AI agents understand visual content they cannot directly perceive. Focus on describing all relevant elements in the image - objects, people, text, colors, spatial relationships, actions, and context. Be precise but concise, organizing information from most to least important. Avoid making assumptions beyond what's visible and clearly indicate any uncertainty. When text appears in images, transcribe it verbatim within quotes. Respond only with factual descriptions without subjective judgments or creative embellishments. Your descriptions should enable an agent to make informed decisions based solely on your analysis.", "title": "System Prompt", "type": "string" }, "temperature": { "default": 0.7, "title": "Temperature", "type": "number" }, "top_p": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "default": null, "title": "Top P" } }, "required": ["image"], "title": "image_analysisArguments", "type": "object" } }

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Nazruden/mcp-openvision'

If you have feedback or need assistance with the MCP directory API, please join our Discord server