Interact & query with Meilisearch (Full-text & semantic search API)
A Model Context Protocol (MCP) server for interacting with Meilisearch through LLM interfaces like Claude.
# Clone repository
git clone <repository_url>
cd meilisearch-mcp
# Create virtual environment and install
uv venv
source .venv/bin/activate # On Windows: .venv\Scripts\activate
uv pip install -e .
MEILI_HTTP_ADDR=http://localhost:7700 # Default Meilisearch URL
MEILI_MASTER_KEY=your_master_key # Optional: Default Meilisearch API key
The server provides tools to view and update connection settings at runtime:
get-connection-settings
: View current connection URL and API key statusupdate-connection-settings
: Update URL and/or API key to connect to a different Meilisearch instanceExample usage through MCP:
// Get current settings
{
"name": "get-connection-settings"
}
// Update connection settings
{
"name": "update-connection-settings",
"arguments": {
"url": "http://new-host:7700",
"api_key": "new-api-key"
}
}
The server provides a flexible search tool that can search across one or all indices:
search
: Search through Meilisearch indices with optional parametersExample usage through MCP:
// Search in a specific index
{
"name": "search",
"arguments": {
"query": "search term",
"indexUid": "movies",
"limit": 10
}
}
// Search across all indices
{
"name": "search",
"arguments": {
"query": "search term",
"limit": 5,
"sort": ["releaseDate:desc"]
}
}
Available search parameters:
query
: The search query (required)indexUid
: Specific index to search in (optional)limit
: Maximum number of results per index (optional, default: 20)offset
: Number of results to skip (optional, default: 0)filter
: Filter expression (optional)sort
: Sorting rules (optional)python -m src.meilisearch_mcp
To use this with Claude Desktop, add the following to your claude_desktop_config.json
:
{
"mcpServers": {
"meilisearch": {
"command": "uvx",
"args": ["-n", "meilisearch-mcp"]
}
}
}
npx @modelcontextprotocol/inspector python -m src.meilisearch_mcp
get-connection-settings
: View current Meilisearch connection URL and API key statusupdate-connection-settings
: Update URL and/or API key to connect to a different instancecreate-index
: Create a new index with optional primary keylist-indexes
: List all available indexesget-index-metrics
: Get detailed metrics for a specific indexget-documents
: Retrieve documents from an index with paginationadd-documents
: Add or update documents in an indexsearch
: Flexible search across single or multiple indices with filtering and sorting optionsget-settings
: View current settings for an indexupdate-settings
: Update index settings (ranking, faceting, etc.)get-keys
: List all API keyscreate-key
: Create new API key with specific permissionsdelete-key
: Delete an existing API keyget-task
: Get information about a specific taskget-tasks
: List tasks with optional filters:
limit
: Maximum number of tasks to returnfrom
: Number of tasks to skipreverse
: Sort order of tasksbatchUids
: Filter by batch UIDsuids
: Filter by task UIDscanceledBy
: Filter by cancellation sourcetypes
: Filter by task typesstatuses
: Filter by task statusesindexUids
: Filter by index UIDsafterEnqueuedAt
/beforeEnqueuedAt
: Filter by enqueue timeafterStartedAt
/beforeStartedAt
: Filter by start timeafterFinishedAt
/beforeFinishedAt
: Filter by finish timecancel-tasks
: Cancel pending or enqueued tasksdelete-tasks
: Delete completed taskshealth-check
: Basic health checkget-health-status
: Comprehensive health statusget-version
: Get Meilisearch version informationget-stats
: Get database statisticsget-system-info
: Get system-level informationMIT
Web and local search using Brave's Search API
Search Engine made for AIs by Exa
RAG Search over your content powered by Inkeep
Search the web using Kagi's search API
Production-ready RAG out of the box to search and retrieve data from your own documents.
An MCP server that connects to Perplexity's Sonar API, enabling real-time web-wide research in conversational AI.
One API for Search, Crawling, and Sitemaps
Search engine for AI agents (search + extract) powered by Tavily
Vectorize MCP server for advanced retrieval, Private Deep Research, Anything-to-Markdown file extraction and text chunking.
RAG MCP for your Agentset data.