F
licenseA
qualityF
maintenanceA Model Context Protocol server that enables Claude to display and interact with images from the local filesystem, allowing users to view images directly in conversations and retrieve image metadata.
3
5
-
Letz AI MCP
Officialby Letz-AI
This server allows you to generate and upscale images using the LetzAI public API.
Create images: Generate images based on text prompts, with customizable settings for mode, dimensions, quality, creativity, watermark, and system version.
Upscale images: Enhance image resolution using either an image ID or URL, with adjustable strength for the upscaling process.
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., "@Letz AI MCPcreate an image of a sunset over mountains with a lake reflection"
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.
LetzAI MCP
Two MCP servers for LetzAI, in one repo.
Hosted — what runs at | Remote, Streamable HTTP, multi-user | |
Local — the original Claude Desktop integration | stdio, single user, your own API key |
Hosted server (server/)
The one to point an MCP client at. Add https://mcp.letz.ai/mcp and authenticate
with a LetzAI integration token as a bearer token.
It is a thin, stateless adapter over the LetzAI public API: every request carries the caller's own token, so permissions and credits resolve to that user or organization. The server holds no key of its own. 24 tools cover image and video generation, image editing, upscaling, trained models and user assets.
See server/README.md for the tool list and local development, and
server/docs/user-guide.md for the end-user setup guide.
Related MCP server: iRAG MCP Server
Local stdio server (stdio/)
The original integration for Claude Desktop, which runs on your own machine with your API key in the client config. Unchanged apart from its path. Prefer the hosted server unless you specifically want a local process.
Deployment
The hosted server runs on GKE (letzai-prod-services-gcp, namespace mcp), behind
the mcp.letz.ai ingress. Kubernetes manifests live in the infrastructure repo
under gcp/workloads/mcp/.
Dev — every push to
mainthat touchesserver/builds and rolls out tomcp.dev.letz.aiautomatically.Prod — deliberate: run the Deploy MCP (prod) workflow, or push a
v*tag.
Available Tools
2 toolsletzai_create_imageC
Create an image using the LetzAI public api
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes | Image prompt to generate a new image. Can also include @tag to generate an image using a model from the LetzAi Platform | |
| width | No | Width of the image should be between 520 and 2160 max pixels. Default is 1600. | |
| height | No | Height of the image should be between 520 and 2160 max pixels. Default is 1600. | |
| quality | No | Defines how many steps the generation should take. Higher is slower, but generally better quality. Min: 1, Default: 2, Max: 5 | |
| creativity | No | Defines how strictly the prompt should be respected. Higher Creativity makes the images more artificial. Lower makes it more photorealistic. Min: 1, Default: 2, Max: 5 | |
| hasWatermark | No | Defines whether to set a watermark or not. Default is true | |
| systemVersion | No | Allowed values: 2, 3. UseLetzAI V2, or V3 (newest). | |
| mode | No | Select one of the different modes that offer different generation settings. Allowed values: default, sigma, turbo. Default is slow but high quality. Sigma is faster and great for close ups. Turbo is fastest, but lower quality. | turbo |
TDQS
C2.9/5.0
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 but only states the basic action. It doesn't cover authentication needs, rate limits, response format, error handling, or any side effects (e.g., whether creation is idempotent or has costs). This leaves significant gaps for an AI agent to understand operational behavior.
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 that directly states the tool's purpose without unnecessary words. It's appropriately sized and front-loaded, making it easy to parse while avoiding redundancy or fluff.
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 8-parameter image generation tool with no annotations and no output schema, the description is insufficient. It lacks details on return values, error conditions, usage constraints, and how it integrates with the sibling tool, leaving the agent with incomplete operational context.
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?
The schema description coverage is 100%, providing detailed documentation for all 8 parameters. The description adds no additional parameter semantics beyond what's already in the schema, so it meets the baseline score of 3 without compensating or enhancing parameter understanding.
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 clearly states the action ('create an image') and the target resource ('using the LetzAI public api'), making the purpose immediately understandable. It distinguishes from the sibling tool 'letzai_upscale_image' by focusing on generation rather than enhancement, though it doesn't explicitly contrast them.
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 or any contextual prerequisites. It mentions the LetzAI public API but doesn't specify use cases, limitations, or when to choose this over other image generation tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
letzai_upscale_imageC
Upscale an image using the LetzAI public api
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| imageId | No | The unique identifier of the image to be upscaled. | |
| imageUrl | No | The URL of the image to be upscaled. Must be a publicly available URL. | |
| strength | Yes | The strength of the upscaling process. Min. 1, Max. 3. |
TDQS
C2.9/5.0
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It mentions using a public API but doesn't disclose critical traits like authentication requirements, rate limits, cost implications, error handling, or what happens to the original image. For a tool that modifies content with no annotation coverage, this leaves significant gaps in understanding its behavior.
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 that states the core purpose without unnecessary words. It's appropriately sized for a straightforward tool and front-loads the essential information. Every word earns its place, making it maximally concise.
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 tool modifies images (implied mutation), has no annotations, and no output schema, the description is incomplete. It doesn't explain what 'upscale' means practically, what format/resolution results are expected, whether the operation is reversible, or what happens if both imageId and imageUrl are provided. For a 3-parameter tool with no structured safety or output information, more context is needed.
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 three parameters thoroughly. The description adds no additional meaning about parameters beyond what's in the schema. It doesn't explain the relationship between imageId and imageUrl, or provide context about strength values. This meets the baseline for high schema coverage.
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 clearly states the action ('Upscale') and resource ('an image') using the LetzAI public API. It distinguishes from the sibling tool 'letzai_create_image' by focusing on upscaling existing images rather than creating new ones. However, it doesn't specify the exact upscaling method or output characteristics, keeping it at a 4 rather than a 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. It doesn't mention prerequisites, limitations, or comparison with the sibling 'letzai_create_image' tool. The agent must infer usage from the tool name and parameters alone, which is insufficient for clear decision-making.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
2 tool updates
- First observed
letzai_create_image - First observed
letzai_upscale_image
TDQS
B3.1/5.0
Scored across 2 tools
Disambiguation5/5
The two tools have completely distinct purposes: one creates images from scratch, while the other upscales existing images. There is no overlap in functionality, and an agent can easily differentiate between them based on their clear descriptions.
Naming Consistency5/5
Both tools follow a consistent 'letzai_verb_noun' pattern with snake_case, using 'create_image' and 'upscale_image' as the core naming structure. This makes them predictable and easy to parse for an agent.
Tool Count2/5
With only two tools, the server feels thin for an AI image generation domain. While create and upscale are core operations, notable gaps like editing, inpainting, or style transfer are missing, making the toolset under-scoped for typical image manipulation workflows.
Completeness2/5
The server covers basic image creation and upscaling but lacks essential operations for a complete image generation surface. There are no tools for editing, modifying, or deleting images, and advanced features like batch processing or style application are absent, leading to potential dead ends for agents.
Maintenance
ActivityMaintained
ResponsivenessNo issues
Related MCP Connectors
Use AI models for chat, image, and video generation from Claude Code and other MCP hosts.
- lightgenOAuthapp.lightgen
Generate and edit images and create short videos inside Claude. Prepaid credits, no subscription.
A Model Context Protocol server for Wix AI tools
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Related MCP Servers
- FlicenseCqualityDmaintenanceA Model Context Protocol server that enables Claude Desktop to generate images using Baidu's iRAG image generation API through a standardized interface.1-
- FlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that enables Claude Code to generate high-quality AI images using ModelsLab API with support for multiple image generation models including Flux, Stable Diffusion, and Midjourney.-
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that enables AI-powered image generation through Stability AI and Black Forest Labs APIs, allowing users to create images from detailed text prompts with customizable settings and comprehensive metadata tracking.MIT