
TypeSense-MCP-Server
MCP Server pour vous connecter à vos collections TypeSense et récupérer des données à l'aide de votre client MCP préféré (Claude / Cursor)
1
Github Watches
1
Github Forks
2
Github Stars
Tacitbase MCP Server
This is a Machine Comprehension Protocol (MCP) server for Tacitbase that provides advanced search capabilities using both Tacitbase's native search and Typesense for enhanced search features.
Project Structure
The project follows a clean, modular architecture:
.
├── models/ # Data structures and types
├── services/ # Business logic and external service interactions
├── handlers/ # Request handlers and routing logic
├── tools/ # Tool registration and configuration
├── main.go # Application entry point
└── README.md # Project documentation
Packages
-
models
: Contains all data structures and types used across the application -
services
: Implements the business logic and external service interactions -
handlers
: Contains the request handlers that process incoming requests -
tools
: Registers the tools available for searching candidates
Features
- Basic keyword search with filtering and sorting
- Vector search for similarity-based matching
- Semantic search with natural language understanding
- Fallback to Tacitbase's native search when needed
- Tool registration for searching candidates
Search Tools
1. Basic Search (search_candidates
)
- Keyword-based search with typo tolerance
- Supports field-specific search
- Filtering and sorting capabilities
- Group by functionality
- Exact matching option
2. Vector Search (vector_search_candidates
)
- Similarity search using vector embeddings
- Ideal for finding candidates with similar profiles
- Supports hybrid search combining vectors with filters
3. Semantic Search (semantic_search_candidates
)
- Natural language understanding
- Automatic embedding generation
- Support for multiple embedding models (OpenAI, SBERT, E5)
- Hybrid search combining semantic understanding with filters
Configuration
Environment Variables
-
TACITBASE_AUTH_TOKEN
: Authentication token for Tacitbase API -
TYPESENSE_API_KEY
: API key for Typesense -
TYPESENSE_HOST
: Typesense host (default: localhost) -
TYPESENSE_PORT
: Typesense port (default: 8108) -
TYPESENSE_PROTOCOL
: Protocol for Typesense (default: http)
Installation
- Install dependencies:
go mod download
- Build the server:
go build -o tb-mcp-server
- Run the server:
./tb-mcp-server
Example Usage
Basic Search
{
"query": "golang developer",
"search_fields": "skills,latest_experience",
"filter_fields": "location:San Francisco",
"sort_by": "latest_experience:desc",
"page": 1,
"per_page": 20
}
Vector Search
{
"vector_query": "[0.1, 0.2, ..., 0.512]",
"filter_fields": "years_of_experience:>5",
"page": 1,
"per_page": 20
}
Semantic Search
{
"query": "experienced team lead with cloud architecture background",
"embedding_model": "openai",
"filter_fields": "years_of_experience:>8",
"page": 1,
"per_page": 20
}
Development
To modify or extend the server:
- Edit
main.go
to add new tools or modify existing ones - Run tests (if any)
- Build and test the server
相关推荐
I find academic articles and books for research and literature reviews.
Confidential guide on numerology and astrology, based of GG33 Public information
Emulating Dr. Jordan B. Peterson's style in providing life advice and insights.
Your go-to expert in the Rust ecosystem, specializing in precise code interpretation, up-to-date crate version checking, and in-depth source code analysis. I offer accurate, context-aware insights for all your Rust programming questions.
Advanced software engineer GPT that excels through nailing the basics.
Take an adjectivised noun, and create images making it progressively more adjective!
Découvrez la collection la plus complète et la plus à jour de serveurs MCP sur le marché. Ce référentiel sert de centre centralisé, offrant un vaste catalogue de serveurs MCP open-source et propriétaires, avec des fonctionnalités, des liens de documentation et des contributeurs.
L'application tout-en-un desktop et Docker AI avec chiffon intégré, agents AI, constructeur d'agent sans code, compatibilité MCP, etc.
Manipulation basée sur Micropython I2C de l'exposition GPIO de la série MCP, dérivée d'Adafruit_MCP230XX
Plateforme d'automatisation de workflow à code équitable avec des capacités d'IA natives. Combinez le bâtiment visuel avec du code personnalisé, de l'auto-hôte ou du cloud, 400+ intégrations.
🧑🚀 全世界最好的 LLM 资料总结 (数据处理、模型训练、模型部署、 O1 模型、 MCP 、小语言模型、视觉语言模型) | Résumé des meilleures ressources LLM du monde.
Miroir dehttps: //github.com/bitrefill/bitrefill-mcp-server
Reviews

user_AH5DGWGy
I've been using the typesense-mcp-server by sourabh-khot65, and it's been amazing. The server's seamless integration with MCP applications and its efficient search capabilities have greatly improved my project's performance. The clear documentation and ease of setup make it a solid choice for developers looking for a reliable search solution. Highly recommend checking it out via the provided GitHub link!