Click on "Install 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., "@image-to-base64 convert this image to base64: https://example.com/photo.jpg"
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.
A Model Context Protocol (MCP) based image to Base64 server designed for Cursor to actually "see" and process images.
🖼️ Image to Base64: Convert local images or remote image URLs to Base64 format
🌐 Remote URL Support: Automatically download and process web images
📋 Multi-format Support: Support PNG, JPEG, GIF, WebP, SVG and other image formats
⚡ High Performance: Use Sharp library for efficient image processing and optimization
🔗 MCP Protocol: Standardized AI tool interface for seamless integration with AI assistants
🎯 Auto Optimization: Intelligently convert to JPEG format to reduce file size
📦 NPX Support: Support running directly through npx without installation
Related MCP server: Extract-Image
Add to your Cursor MCP configuration file:
{
"mcpServers": {
"image-to-base64": {
"command": "npx",
"args": ["@code-tinker/mcp-image-to-base64"]
}
}
}
将图片地址转为base64然后AI才可以真正看到这张图片。支持本地文件路径和远程URL。
| Name | Required | Description | Default |
|---|---|---|---|
| image_path | Yes | 图片路径，可以是本地文件路径或远程URL |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the behavioral burden. It clearly discloses that the tool performs a conversion to base64 and supports both local and remote image sources, with no contradiction between stated behavior and annotations.
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 short sentences that front-load the core transformation, explain its purpose, and list the supported input types. Every sentence adds value with no redundancy.
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?
For a one-parameter utility with no output schema, the description is largely sufficient: it states the input types, the transformation, and why the AI should use it. It stops short of detailing the exact output format or failure behavior, which prevents a perfect score.
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?
The schema already documents image_path at 100% coverage, including support for local paths and remote URLs. The description adds context about why the AI needs this conversion, but does not substantially expand the parameter meaning beyond the schema.
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 states a specific action ('将图片地址转为base64') and an explicit purpose: enabling the AI to actually see the image. It clearly identifies the resource type and the expected outcome, making the tool's purpose unambiguous even without sibling tools.
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?
The description makes the usage context explicit: use it when the AI needs to see an image. It also enumerates accepted input forms (local file path and remote URL), which is the key selection criterion. Since no sibling tools are present, there is no need to name alternatives.
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. Dates show when Glama detected each change.
v1.0.2image_to_base64Only one tool exists, so there is no possible confusion with other tools. The tool's purpose is clear and unambiguous.
The single tool uses a descriptive snake_case name that aligns with the server's purpose, and there are no inconsistent naming patterns to compare.
For a single-purpose utility server, one tool is well-scoped and appropriate. Additional tools would be unnecessary or out of scope.
The tool fully covers the server's stated purpose: converting images to base64 from both local paths and remote URLs. There are no missing operations within this narrow domain.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Convert images to PNG, JPEG, WebP, or AVIF through one public remote MCP tool.
OCR, transcription, file extraction, and image generation for AI agents via MCP.
Generate AI images and videos from any compatible MCP client.
AI-powered image processing via GPU. Remove backgrounds and upscale images (2x/4x) directly from any MCP client. OAuth 2.1 authenticated, returns processed images inline with download links. Free credits on signup at maskr.io.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/code-tinker/image2base64-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
