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., "@banana-prompts-mcp search for prompts tagged 'cyberpunk'"
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.
This MCP (Model Context Protocol) server allows you to search for high-quality AI art prompts directly from Banana Prompts.
Explore a curated collection of Nano Banana prompts to inspire your next creation.
Search by Tags: Find prompts by specific categories or styles (e.g., "Cyberpunk", "Portrait", "Oil Painting").
Search by Query: Perform a general keyword search across prompt titles and content.
Natural Integration: Each result includes a direct link to the full prompt and high-resolution images on the Banana Prompts website.
Related MCP server: Nanana AI Image Generation Server
To use this server with Claude Desktop or any other MCP-compatible client, follow these steps:
Node.js (v18 or higher recommended)
An MCP-compatible client (like Claude Desktop)
Clone the repository or download the files:
git clone https://github.com/Banana-Prompts/banana-prompts-mcp.git
cd banana-prompts-mcp
npm install
npm run buildAdd the following to your claude_desktop_config.json:
{
"mcpServers": {
"banana-prompts": {
"command": "node",
"args": ["/path/to/banana-prompts-mcp/dist/index.js"]
}
}
}Replace /path/to/banana-prompts-mcp/dist/index.js with the actual absolute path to the compiled dist/index.js file.
Once configured, you can ask Claude to:
"Find some cyberpunk prompts on Banana Prompts"
"Search Banana Prompts for sunset landscape prompts"
"Show me prompts tagged with 'watercolor' from bananaprompts.fun"
search_prompts_by_tags: Input an array of tags to filter prompts.
search_prompts_by_query: Input a search string to find matching prompts.
Built by the team at Banana Prompts (bananaprompts.fun).
Search for AI art prompts on Banana Prompts using a general search query.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | The search terms (e.g., 'futuristic city') | |
| page | No | Page number for pagination (default: 1) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description bears full responsibility for disclosing behavioral traits. It only states the tool's purpose and says nothing about pagination, result limits, error behavior, or any side effects. The description is too thin for an agent to understand the tool's behavior beyond its basic function.
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 a single sentence that conveys the essential purpose without any extraneous information. It is front-loaded and efficient, with every word contributing to the understanding of the tool.
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 is simple (2 params, no output schema, no annotations), but the description does not address what the tool returns or any behavioral nuances. While it adequately states the purpose, it lacks completeness for an agent to fully understand the tool's output or constraints. It is minimally viable but not comprehensive.
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 both parameters already have clear descriptions in the input schema. The tool description adds no additional parameter semantics beyond what the schema provides. According to guidelines, baseline is 3, and no extra value is added.
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 clearly states the verb 'Search', the resource 'AI art prompts', the platform 'Banana Prompts', and the modality 'using a general search query'. It distinguishes from the sibling tool search_prompts_by_tags by indicating a general query approach, making the purpose specific and unambiguous.
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 provides no guidance on when to use this tool versus alternatives like search_prompts_by_tags. It does not mention any prerequisites, constraints, or conditions for its use. The agent receives no help in choosing between tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search for AI art prompts on Banana Prompts by one or more tags.
| Name | Required | Description | Default |
|---|---|---|---|
| tags | Yes | An array of tags to search for (e.g., ['Portrait', 'Cyberpunk']) | |
| page | No | Page number for pagination (default: 1) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose any behavioral traits beyond the basic search operation. Missing details on pagination, rate limits, authentication, or response format.
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 a single, front-loaded sentence that efficiently conveys the tool's purpose without extraneous words.
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 simple search tool with two parameters and no output schema, the description is minimally adequate but lacks details on pagination behavior, default page, and response structure.
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 coverage is 100%, so the schema already fully documents both parameters. The description adds no additional information beyond the schema's descriptions, resulting in no extra value.
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 clearly states the verb 'Search', the resource 'AI art prompts', and the method 'by one or more tags'. It directly distinguishes from the sibling tool 'search_prompts_by_query' which likely uses a text query.
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 implies usage when tags are available but lacks explicit guidance on when to use this tool versus the sibling tool. No exclusions or alternative suggestions are provided.
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.
v1.0.0search_prompts_by_querysearch_prompts_by_tagsScored across 2 tools
The two tools have clearly distinct purposes: one searches by a general query, the other by tags. There is no overlap in functionality, making them easy to distinguish for an agent.
Both tools follow the consistent verb_noun pattern 'search_prompts_by_<criterion>', making the naming predictable and intuitive.
Only two tools is very few for a server. Even though it focuses on search, the minimal count suggests an underdeveloped surface that may not meet diverse agent needs.
Only search operations are provided; there are no tools for creating, updating, or deleting prompts. This leaves obvious gaps for any workflow beyond simple lookup.
The Wikipedia of AI prompts: search 900+ curated prompts by model, style and type, in 7 languages
Create images and videos from prompts, with options for image mixing, reference images, and start/…
Search published AI prompt products on PromptBase.art: titles, prices, ratings, URLs.
Generate logos, social posts, app screenshots, comic panels & visual-novel assets from prompts.