Skip to main content
Glama

inpaint

Remove unwanted elements from images using AI-powered inpainting. Select mask shapes and positions to replace specific areas with new content generated from text prompts.

Instructions

Inpaint an image using a mask

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
imageYesInput image path
promptYesText prompt for inpainting
mask_shapeNoShape of the maskcircle
positionNoPosition of the maskcenter
outputNoOutput filenameinpainted.jpg

Implementation Reference

  • MCP tool handler for 'inpaint': validates InpaintArgs, builds command line arguments for the Python CLI, executes via runPythonCommand, and returns the output.
    case 'inpaint': {
        const args = request.params.arguments as InpaintArgs;
        // Validate required fields
        const image = this.validateRequiredString(args.image, 'image');
        const prompt = this.validateRequiredString(args.prompt, 'prompt');
    
        const cmdArgs = ['inpaint'];
        cmdArgs.push('--image', image);
        cmdArgs.push('--prompt', prompt);
        if (args.mask_shape) cmdArgs.push('--mask-shape', args.mask_shape);
        if (args.position) cmdArgs.push('--position', args.position);
        if (args.output) cmdArgs.push('--output', args.output);
    
        const output = await this.runPythonCommand(cmdArgs);
        return {
            content: [{ type: 'text', text: output }],
        };
    }
  • src/index.ts:215-249 (registration)
    Registration of the 'inpaint' tool in the ListTools response, including name, description, and JSON input schema.
    {
        name: 'inpaint',
        description: 'Inpaint an image using a mask',
        inputSchema: {
            type: 'object',
            properties: {
                image: {
                    type: 'string',
                    description: 'Input image path',
                },
                prompt: {
                    type: 'string',
                    description: 'Text prompt for inpainting',
                },
                mask_shape: {
                    type: 'string',
                    description: 'Shape of the mask',
                    enum: ['circle', 'rectangle'],
                    default: 'circle',
                },
                position: {
                    type: 'string',
                    description: 'Position of the mask',
                    enum: ['center', 'ground'],
                    default: 'center',
                },
                output: {
                    type: 'string',
                    description: 'Output filename',
                    default: 'inpainted.jpg',
                },
            },
            required: ['image', 'prompt'],
        },
    },
  • TypeScript interface InpaintArgs defining the typed arguments for the inpaint tool handler.
    export interface InpaintArgs {
      image: string;
      prompt: string;
      mask_shape?: MaskShape;
      position?: MaskPosition;
      output?: string;
    }
  • Core implementation of inpainting in FluxAPI: creates procedural mask, encodes image and mask, submits to BFL API /v1/flux-pro-1.0-fill, polls and returns result URL.
    def inpaint(self, image_path: str, prompt: str, mask_shape: str = 'circle', position: str = 'center') -> Optional[str]:
        """Inpaint an image using a mask."""
        base_image = Image.open(image_path)
        mask = self.create_mask(base_image.size, shape=mask_shape, position=position)
        
        mask_path = 'temp_mask.jpg'
        mask.save(mask_path)
        
        payload = {
            "image": self.encode_image(image_path),
            "mask": self.encode_image(mask_path),
            "prompt": prompt,
            "steps": 50,
            "guidance": 60,
            "output_format": "jpeg",
            "safety_tolerance": 2
        }
        
        response = requests.post(
            f"{self.base_url}/v1/flux-pro-1.0-fill",
            json=payload,
            headers=self.headers
        )
        
        os.remove(mask_path)
        
        task_id = response.json().get('id')
        if not task_id:
            return None
            
        result = self.get_task_result(task_id)
        if result and result.get('result', {}).get('sample'):
            return result['result']['sample']
        return None
  • Supporting utility to create procedural mask image for inpainting based on shape ('circle'/'rectangle') and position ('center'/'ground').
    def create_mask(self, size: tuple, shape: str = 'rectangle', position: str = 'center') -> Image:
        """Create a mask for inpainting."""
        mask = Image.new('L', size, 0)
        draw = ImageDraw.Draw(mask)
        
        width, height = size
        
        if position == 'ground':
            horizon_y = height * 0.65
            y_start = horizon_y - (height * 0.05)
            points = [
                (0, y_start),
                (0, height),
                (width, height),
                (width, y_start)
            ]
            draw.polygon(points, fill=255)
        else:
            x1 = width * 0.25
            y1 = height * 0.25
            x2 = width * 0.75
            y2 = height * 0.75
            
            if shape == 'rectangle':
                draw.rectangle([x1, y1, x2, y2], fill=255)
            else:  # circle
                center = (width // 2, height // 2)
                radius = min(width, height) // 4
                draw.ellipse([center[0] - radius, center[1] - radius,
                             center[0] + radius, center[1] + radius], fill=255)
        
        return mask
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the action ('inpaint') but doesn't explain what inpainting entails (e.g., filling masked areas based on a prompt), potential side effects, permissions needed, or output behavior. This leaves significant gaps for a tool that modifies images.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence with zero waste—'Inpaint an image using a mask'—making it highly concise and front-loaded. Every word earns its place by conveying the core action and resource.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of an image inpainting tool with no annotations and no output schema, the description is insufficient. It doesn't explain what inpainting does, how the output is handled, or any behavioral traits, leaving the agent with incomplete context for proper tool selection and invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all parameters (image, prompt, mask_shape, position, output) with descriptions and enums. The description adds no additional meaning beyond what the schema provides, such as explaining how the prompt influences inpainting or how mask shape/position interact. Baseline 3 is appropriate when the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Inpaint an image using a mask' clearly states the action (inpaint) and resource (image with mask), making the purpose understandable. However, it doesn't differentiate from sibling tools like 'img2img' or 'generate', which might also involve image manipulation, so it's not a perfect 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives like 'img2img' or 'generate'. It lacks context about specific use cases, prerequisites, or exclusions, leaving the agent to infer usage based on the name alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

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/jmanhype/mcp-flux-studio'

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