🚀 Type-Aware MCP Server
A server implementing the Model Context Protocol (MCP) that provides type-aware search capabilities for AI models. This server enables large language models to discover, search, and analyze data stored in type-aware collections.
🚀 Quick Start
The Type-Aware MCP Server is a powerful tool that enables large language models to perform type-aware searches on data stored in collections. Below is a quick overview of how to get started.
🎥 Demo
✨ Features
Resources
- List and access collections via
typesense://URIs. - Each collection has a name, description, and the number of documents.
- JSON MIME type is used for schema access.
Tools
-
typesense_query
- Search for documents in type-aware collections with powerful filtering capabilities.
- Input: Query text, collection name, search fields, filters, sorting options, limit.
- Returns matching documents with relevance scores.
-
typesense_get_document
- Retrieve a specific document from a collection by ID.
- Input: Collection name, document ID.
- Returns the full document data.
-
typesense_collection_stats
- Get statistics for a type-aware collection.
- Input: Collection name.
- Returns collection metadata, the number of documents, and schema information.
Prompts
-
analyze_collection
- Analyze the structure and content of a collection.
- Input: Collection name.
- Output: Insights on schema, data types, and statistics.
-
search_suggestions
- Get valid search query suggestions.
- Input: Collection name.
- Output: Recommended search strategies based on the collection schema.
📦 Installation
Using npm
# Global installation
npm install -g typesense-mcp-server
# Local installation
npm install typesense-mcp-server
Using mcp-get
npx @michaellatman/mcp-get@latest install typesense-mcp-server
🔧 Building and Development
To build from source and run tests:
git clone git://github.com/yourusername/typesense-mcp-server.git
cd typesense-mcp-server
npm install
npm run dev
📄 License
This MCP server is released under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please refer to the LICENSE file in the project repository.














