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., "@Riftrunner AI MCP Server What models are available?"
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.
Riftrunner AI - AI-Powered RPG Adventures
A Model Context Protocol server that exposes the canonical Riftrunner AI knowledge surface — models, prompts, and chat workflows, pricing, FAQ, official links — to MCP-compatible AI clients such as Claude Desktop, Cursor, Windsurf, and Continue. Read-only, no API keys, no quota, ~50 ms cold start.
Official website: https://riftrunnerai.online
Riftrunner AI is a browser-based platform for generating and editing images and videos using Google's Gemini 3 Pro and Veo 3 models. Users can create content from text prompts or uploaded images without installing any software. The platform bundles several AI models — including Flux Pro, Qwen, and Seedream variants — under a single interface, alongside a suite of focused editing tools. It is designed to serve both casual creators who want quick results and professionals who need commercial-grade output at volume. A free tier lets anyone start generating immediately, while paid plans add higher resolution, faster processing, and commercial usage rights.
Related MCP server: Flux-2 Online MCP
Text-to-image generation using Gemini 3 Pro with support for multiple aspect ratios and quality settings.
Veo 3.1 video generation that converts text prompts or still images into short AI-produced video clips.
Nano Banana Editor for character-consistent image editing with style transfer and iterative refinement.
Focused image tools including Background Remover, Hairstyle Changer, Image Enhancer, Text Remover, and Product Photography presets.
Multi-model comparison view that renders the same prompt across different AI models side by side so users can pick the best result.
AI 3D Figure and Professional Photo generators for portrait and product work that requires a consistent, polished look.
A social media manager generates batch product photos with clean backgrounds for an e-commerce catalog in minutes, without a photography studio.
A digital artist uses the image-to-image workflow to refine a rough sketch into a finished illustration across several style iterations.
A content creator produces short AI video clips from storyboard prompts to pre-visualize a scene before committing to full production.
A developer integrates Riftrunner AI's API into an internal tool to automate visual asset generation for a marketing team.
A small business owner creates professional portrait-style headshots using the Professional Photo preset without hiring a photographer.
Riftrunner AI targets digital content creators, marketing teams, and visual professionals who need high-quality AI-generated images and video without managing multiple separate tools. It suits social media managers producing regular content, e-commerce operators who need product imagery at scale, indie developers building visual assets for projects, and digital artists who use AI generation as part of a broader creative workflow. The free tier makes it approachable for individuals experimenting with AI visuals, while the API access and commercial licensing on paid plans address the needs of studios, agencies, and businesses that require reliable output rights and integration with existing production pipelines.
list_modelsReturn the canonical list of chat models exposed on the site, with capability notes. (Riftrunner AI)
Input: no parameters. Returns: text/markdown.
get_pricingReturn the canonical pricing entry point for Riftrunner AI.
Input: no parameters. Returns: text/markdown.
get_official_linksReturn the canonical list of official links for Riftrunner AI (website, support, docs when available).
Input: no parameters. Returns: text/markdown.
site://riftrunner-ai-online/models — Supported chat models and capability notes.
site://riftrunner-ai-online/pricing — Canonical pricing entry point.
site://riftrunner-ai-online/faq — Short FAQ generated from public site metadata.
site://riftrunner-ai-online/links — Canonical URLs to share with users.
tell_me_about_riftrunner_ai_onlineSummarize what the site is, who it's for, and how it works. — Riftrunner AI
start_chat_session_riftrunner_ai_onlineOpen a chat-evaluation session against the site's models, with sensible defaults. — Riftrunner AI
npx -y @smithery/cli install riftrunner-ai-online-mcp --client claude(Replace claude with cursor, windsurf, or continue for those clients.)
git clone https://github.com/rocnubie/riftrunner-ai-online-mcp.git
cd riftrunner-ai-online-mcp
pnpm installThen add to your MCP client config (claude_desktop_config.json for Claude Desktop, mcp.json for Cursor / Windsurf / Continue):
{
"mcpServers": {
"riftrunner-ai-online-mcp": {
"command": "node",
"args": [
"/absolute/path/to/riftrunner-ai-online-mcp/src/index.mjs"
]
}
}
}npx @modelcontextprotocol/inspector node src/index.mjsWebsite: https://riftrunnerai.online
Pricing: https://riftrunnerai.online/pricing
Support: support@riftrunnerai.online
pnpm install
pnpm start # run the server over stdioMIT
Return the canonical list of official links for Riftrunner AI (website, support, docs when available).
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided. The description mentions it returns a list of links but does not disclose behavioral details like update frequency, caching, or error handling. For a simple tool, this is adequate but not comprehensive.
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?
One sentence that is front-loaded with the action 'Return' and includes all necessary detail without any fluff. Every word earns its place.
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?
Given the tool has no parameters and no output schema, the description provides sufficient context for an agent to know what the tool does. However, it could hint at the format or stability of the links.
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 tool has no parameters, and the input schema covers 100% of parameter definitions. The description adds no parameter-specific meaning, which is acceptable as baseline for zero parameters.
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 it returns the canonical list of official links for Riftrunner AI, covering website, support, and docs. It distinguishes itself from sibling tools (list_models, get_pricing) by its specific focus on links.
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 when to use (when official links are needed). While it does not explicitly state when not to use it or provide alternatives, the tool has zero parameters, making its usage straightforward.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return the canonical pricing entry point for Riftrunner AI.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries the full burden. It discloses that the tool returns data, but does not mention any behavioral traits (e.g., cost, rate limits, or idempotency). For a simple getter, the lack of negative side effects is implied but not stated.
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 of 8 words, containing only essential information. No redundancy or fluff.
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 description defines the tool's purpose minimally. Without an output schema, the agent does not know the structure of the returned pricing entry point. Given the simple nature (0 params), it is adequate but could clarify what 'canonical pricing entry point' means.
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?
There are no parameters, so schema coverage is 100% and the description adds no parameter-level detail. The baseline for 0 parameters is 4, and the description does not contradict or add confusion.
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 uses a specific verb ('Return') and identifies the resource ('canonical pricing entry point for Riftrunner AI'). It clearly distinguishes from sibling tools like list_models and get_official_links, which cover different domains.
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 pricing information is needed, but does not provide explicit when-to-use or when-not-to-use guidance. However, given the tool's simplicity and lack of alternatives for pricing, it is clear enough.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return the canonical list of chat models exposed on the site, with capability notes. (Riftrunner AI)
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden for behavioral disclosure. It does not mention that the tool is read-only, has no side effects, or any rate limits or auth requirements, leaving significant gaps.
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 is clear and front-loaded, but includes an unnecessary parenthetical 'Riftrunner AI' that adds no value. It is concise but could be more streamlined.
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 tool with no parameters and no output schema, the description adequately states the return value (list with capability notes). It is complete enough given the tool's low complexity.
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 tool has zero parameters and 100% schema description coverage, so the description need not add parameter details. The baseline of 4 is appropriate as no additional semantics are required.
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 tool returns a canonical list of chat models with capability notes. The verb 'Return' and resource 'list of chat models' are specific, and the tool is easily distinguished from siblings get_pricing and get_official_links.
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 does not provide explicit guidance on when to use this tool over alternatives. It only states the basic function, leaving usage context implied rather than stated.
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.
v0.1.0get_official_linksget_pricinglist_modelsEach tool has a clearly distinct purpose: listing models, retrieving pricing, and obtaining official links. No overlap in functionality.
All tool names follow a consistent verb_noun pattern (list_models, get_pricing, get_official_links), making them predictable and easy to understand.
With 3 tools, the server is focused and well-scoped, covering the essential informational needs for the Riftrunner AI platform without unnecessary clutter.
The tool set covers the stated purpose of providing canonical information (models, pricing, links). However, it lacks tools for direct AI interaction or usage, which might be expected given the server's name.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Read-only MCP server for RZ AI Labs — query its services, workshops, and contact info.
Hosted MCP server for live public-data APIs and Skills for AI agents.
Public, read-only MCP server for FarmNeural company facts, packages, and capabilities.
Talk to your public-facing AI from any MCP client — Claude, ChatGPT, Cursor, Cline, Windsurf.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/rocnubie/riftrunner-ai-online-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
