Meilisearch

Meilisearch MCP Server

A Model Context Protocol (MCP) server for interacting with Meilisearch through LLM interfaces like Claude.

Features

• Index and document management
• Settings configuration and management
• Task monitoring and API key management
• Built-in logging and monitoring tools
• Dynamic connection configuration to switch between Meilisearch instances
• Smart search across single or multiple indices
• This is a Python implementation, there is Typescript integration if you need to work with a Meilisearch MCP server within the browser

Installation

1# Clone repository
2git clone <repository_url>
3cd meilisearch-mcp
4
5# Create virtual environment and install
6uv venv
7source .venv/bin/activate  # On Windows: .venv\Scripts\activate
8uv pip install -e .

Requirements

• Python ≥ 3.9
• Running Meilisearch instance
• Node.js (for testing with MCP Inspector)

Usage

Environment Variables

1MEILI_HTTP_ADDR=http://localhost:7700  # Default Meilisearch URL
2MEILI_MASTER_KEY=your_master_key       # Optional: Default Meilisearch API key

Dynamic Connection Configuration

The server provides tools to view and update connection settings at runtime:

• get-connection-settings: View current connection URL and API key status
• update-connection-settings: Update URL and/or API key to connect to a different Meilisearch instance

Example usage through MCP:

1// Get current settings
2{
3  "name": "get-connection-settings"
4}
5
6// Update connection settings
7{
8  "name": "update-connection-settings",
9  "arguments": {
10    "url": "http://new-host:7700",
11    "api_key": "new-api-key"
12  }
13}

Search Functionality

The server provides a flexible search tool that can search across one or all indices:

• search: Search through Meilisearch indices with optional parameters

Example usage through MCP:

1// Search in a specific index
2{
3  "name": "search",
4  "arguments": {
5    "query": "search term",
6    "indexUid": "movies",
7    "limit": 10
8  }
9}
10
11// Search across all indices
12{
13  "name": "search",
14  "arguments": {
15    "query": "search term",
16    "limit": 5,
17    "sort": ["releaseDate:desc"]
18  }
19}

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)

Running the Server

1python -m src.meilisearch_mcp

Usage with Claude Desktop

To use this with Claude Desktop, add the following to your claude_desktop_config.json:

1{
2  "mcpServers": {
3    "meilisearch": {
4      "command": "uvx",
5      "args": ["-n", "meilisearch-mcp"]
6    }
7  }
8}

Testing with MCP Inspector

1npx @modelcontextprotocol/inspector python -m src.meilisearch_mcp

Available Tools

Connection Management

• get-connection-settings: View current Meilisearch connection URL and API key status
• update-connection-settings: Update URL and/or API key to connect to a different instance

Index Management

• create-index: Create a new index with optional primary key
• list-indexes: List all available indexes
• get-index-metrics: Get detailed metrics for a specific index

Document Operations

• get-documents: Retrieve documents from an index with pagination
• add-documents: Add or update documents in an index

Search

• search: Flexible search across single or multiple indices with filtering and sorting options

Settings Management

• get-settings: View current settings for an index
• update-settings: Update index settings (ranking, faceting, etc.)

API Key Management

• get-keys: List all API keys
• create-key: Create new API key with specific permissions
• delete-key: Delete an existing API key

Task Management

• get-task: Get information about a specific task
• get-tasks: List tasks with optional filters:
  • limit: Maximum number of tasks to return
  • from: Number of tasks to skip
  • reverse: Sort order of tasks
  • batchUids: Filter by batch UIDs
  • uids: Filter by task UIDs
  • canceledBy: Filter by cancellation source
  • types: Filter by task types
  • statuses: Filter by task statuses
  • indexUids: Filter by index UIDs
  • afterEnqueuedAt/beforeEnqueuedAt: Filter by enqueue time
  • afterStartedAt/beforeStartedAt: Filter by start time
  • afterFinishedAt/beforeFinishedAt: Filter by finish time
• cancel-tasks: Cancel pending or enqueued tasks
• delete-tasks: Delete completed tasks

System Monitoring

• health-check: Basic health check
• get-health-status: Comprehensive health status
• get-version: Get Meilisearch version information
• get-stats: Get database statistics
• get-system-info: Get system-level information

Contributing

1. Fork repository
2. Create feature branch
3. Commit changes
4. Create pull request

License

MIT