Sponsored by Deepsite.site

Calypso Multimodal RAG

Created By
Calypso22 days ago
Launch a hosted Gemini File Search true multimodal RAG layer that answers from your PDFs, docs, screenshots, charts, diagrams, help center, FAQs, and images with citations people can verify.
Content

Calypso MCP

Calypso MCP brings multimodal RAG to your AI tools and workflows with a grounded answer layer built for websites, AI agents, support copilots, internal knowledge assistants, and product experiences.

Instead of relying on generic model memory, Calypso retrieves from your actual source material, including PDFs, docs, screenshots, diagrams, charts, help content, and structured knowledge, so answers stay source-backed, explainable, and production-ready.

Why teams use Calypso MCP

  • Grounded answers, not generic guesses
    Query your knowledge with retrieval-backed responses instead of unverified model output.

  • Multimodal RAG support
    Work across PDFs, documentation, help center content, screenshots, diagrams, images, and internal files.

  • Built for AI agents and real product surfaces
    Use the same answer layer across website chat, support, sales assistants, workflow automation, and custom agent experiences.

  • Agent-store and knowledge-store uploads
    Upload files directly to a specific RAG agent store for retrieval-backed chat, or ingest them into a broader durable knowledge store for indexing.

  • RAG-first file semantics
    Agent file attachments use retrieval-backed behavior with rag_policy, so uploaded files are treated as searchable context rather than default inline attachments.

Included MCP tools

calypso-rag-agent

Query the Calypso RAG agent for grounded answers over your configured knowledge base.

calypso-upload-agent-file

Upload a file into the agent store and receive a compatible file_id for retrieval-backed RAG chat.

calypso-upload-knowledge-file

Upload a file into the knowledge store for durable indexing and shared corpus ingestion.

Best fit for

  • AI support assistants
  • Sales enablement copilots
  • Internal knowledge agents
  • Website answer widgets
  • Workflow automation
  • Product-embedded RAG experiences

What makes it different

Calypso is designed as a grounded answer layer. That means:

  • retrieval over real source material
  • reusable deployment across multiple surfaces
  • multimodal knowledge handling
  • strong fit for operational and customer-facing AI systems

If you need source-backed answers from PDFs, docs, visuals, and knowledge files inside an MCP-compatible workflow, Calypso MCP gives you a clean path from upload to retrieval to grounded response.

Server Config

{
  "mcpServers": {
    "calypso-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "calypso-mcp"
      ],
      "env": {
        "CALYPSO_API_KEY": "YOUR_CALYPSO_API_KEY",
        "CALYPSO_API_BASE_URL": "https://api.calypso.so/v1"
      }
    }
  }
}
Recommend Servers
TraeBuild with Free GPT-4.1 & Claude 3.7. Fully MCP-Ready.
EdgeOne Pages MCPAn MCP service designed for deploying HTML content to EdgeOne Pages and obtaining an accessible public URL.
AiimagemultistyleA Model Context Protocol (MCP) server for image generation and manipulation using fal.ai's Stable Diffusion model.
Tavily Mcp
Playwright McpPlaywright MCP server
MCP AdvisorMCP Advisor & Installation - Use the right MCP server for your needs
Howtocook Mcp基于Anduin2017 / HowToCook (程序员在家做饭指南)的mcp server,帮你推荐菜谱、规划膳食,解决“今天吃什么“的世纪难题; Based on Anduin2017/HowToCook (Programmer's Guide to Cooking at Home), MCP Server helps you recommend recipes, plan meals, and solve the century old problem of "what to eat today"
BlenderBlenderMCP connects Blender to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Blender. This integration enables prompt assisted 3D modeling, scene creation, and manipulation.
Zhipu Web SearchZhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.
DeepChatYour AI Partner on Desktop
ChatWiseThe second fastest AI chatbot™
Amap Maps高德地图官方 MCP Server
CursorThe AI Code Editor
Baidu Map百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Y GuiA web-based graphical interface for AI chat interactions with support for multiple AI models and MCP (Model Context Protocol) servers.
Visual Studio Code - Open Source ("Code - OSS")Visual Studio Code
WindsurfThe new purpose-built IDE to harness magic
Jina AI MCP ToolsA Model Context Protocol (MCP) server that integrates with Jina AI Search Foundation APIs.
Serper MCP ServerA Serper MCP Server
MiniMax MCPOfficial MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.
RedisA Model Context Protocol server that provides access to Redis databases. This server enables LLMs to interact with Redis key-value stores through a set of standardized tools.