Meilisearch MCP Server
Meilisearch indices, search queries, and task monitoring for MCP-ready AI assistants.
Data last scanned today · Reviewed today
Overview
Meilisearch MCP Server enables AI assistants to interface directly with Meilisearch instances via the Model Context Protocol. By leveraging this stdio-based server, users can manage search indices, configure settings, and execute complex search queries using natural language through their AI agents. The server is built on the Python MCP SDK and provides comprehensive support for index management, real-time task monitoring, and API key handling. It is designed to provide structured data outputs that adhere to current MCP specifications, facilitating seamless integration for any LLM client that supports the protocol.
Our verdict
With a security score of 45/100, this server is classified as high-risk. This rating is primarily due to the fact that it is a community-maintained project rather than an official vendor release, and critical aspects such as authentication methods and read-only mode safety have not yet been editorially reviewed. It is suitable for experimentation and non-sensitive development environments, but should not be deployed in production systems handling private or restricted data until further security vetting occurs.
- Built using the modern MCP Python SDK v2
- Zero direct dependencies minimizes supply-chain surface area
- Supports granular index management and search configuration
- Provides structured content outputs per latest MCP specifications
- Community-maintained rather than supported by the official Meilisearch vendor
- Authentication mechanisms have not undergone editorial security review
- Read-only mode functionality lacks independent verification
- Project lacks a dedicated homepage link for verified documentation
Tools
| Tool | Description | Risk |
|---|---|---|
| get-connection-settings | View current Meilisearch connection URL and API key status | low |
| update-connection-settings | Update URL and/or API key to connect to a different instance | medium |
| create-index | Create a new index with optional primary key | medium |
| list-indexes | List all available indexes | low |
| delete-index | Delete an existing index and all its documents | high |
| get-index-metrics | Get detailed metrics for a specific index | low |
| get-documents | Retrieve documents from an index with pagination | low |
| add-documents | Add or update documents in an index | medium |
| search | Flexible search across single or multiple indices with filtering and sorting options | low |
| get-settings | View current settings for an index | low |
Compatibility
| Client | Local | Docker | Remote | Read-only |
|---|---|---|---|---|
| Claude Desktop | ||||
| Cursor | ||||
| VS Code | ||||
| Windsurf | ||||
| ChatGPT |
Frequently asked questions
›What are the system prerequisites for running this MCP server?
You need Python 3.10 or higher, a running Meilisearch instance, and an MCP-compatible client like Claude Desktop or OpenAI agents.
›How does the server communicate with the MCP client?
The server currently uses the stdio transport protocol to facilitate communication between the AI assistant and the Meilisearch instance.
›Can I use this server in containerized environments like n8n?
Yes, you can run the server via a Docker container by providing the MEILI_HTTP_ADDR and MEILI_MASTER_KEY environment variables.
›Is there a TypeScript version available?
Yes, a TypeScript implementation of the Meilisearch MCP server is available through a separate repository.
Alternatives
Badge
Maintain this server? Add the live badge to your README.