Meilisearch

A Model Context Protocol server that enables AI assistants to interact with Meilisearch through natural conversation. Provides lightning-fast search capabilities with full feature access including index management, document operations, search with advanced filtering, settings configuration, API key management, and system monitoring.

Key Features

• Index & Document Management - Create, update, and manage search indices and documents
• Smart Search - Search across single or multiple indices with advanced filtering, sorting, and facets
• Semantic & Hybrid Search - Support for vector-based semantic search and hybrid keyword+semantic search
• Settings Configuration - Fine-tune search relevancy, ranking rules, faceting, and typo tolerance
• Task Monitoring - Track indexing progress and system operations
• API Key Management - Secure access control with granular permissions
• Health Monitoring - Monitor instance health and system statistics
• Dynamic Connections - Switch between Meilisearch instances on the fly

Installation Options

Using uvx (recommended)

uvx -n meilisearch-mcp

Using pip

pip install meilisearch-mcp

Using Docker

docker pull getmeili/meilisearch-mcp:latest
docker run -it \
  -e MEILI_HTTP_ADDR=http://your-meilisearch:7700 \
  -e MEILI_MASTER_KEY=your-master-key \
  getmeili/meilisearch-mcp:latest

Usage Examples

Create an index:

Create a new index called 'products' with 'id' as the primary key

Add documents:

Add some products to the index

Search with filters:

Search for products under $50 with 'electronics' in the category

Multi-index search:

Search across all my indices for 'machine learning' and sort by date

Prerequisites

Requires a running Meilisearch instance. Quick start:

docker run -d -p 7700:7700 getmeili/meilisearch:v1.28

Or install via Homebrew:

brew install meilisearch
meilisearch