Meilisearch
About
Integrates with Meilisearch to enable powerful search operations with filtering and sorting capabilities for structured data retrieval
Details
- Author
- cnosuke
- Repository
- cnosuke/mcp-meilisearch
- Categories
- Developer Tools, Design, Workplace, File Management, AI, Search, Infrastructure, Frontend, Knowledge Base
Jump to
- Lightweight and fast MCP server implemented in Go
- Seamless integration with Meilisearch API
- Interface compliant with the MCP protocol
- Support for key features including search, index management, and document operations
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
MeilisearchCommand (node, npx, python, etc.)./bin/mcp-meilisearchArguments-
Argument 1
server -
Argument 2
--no-logs -
Argument 3
--log -
Argument 4
path_to_log_file
Environment-
MEILISEARCH_HOST
http://localhost:7700 -
MEILISEARCH_API_KEY
api_key
Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
-
Argument 1
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Use the config.yml file to configure connection settings to the Meilisearch server:
```yaml
make deps
health_check
Check the status of the Meilisearch server. Parameters: None. Returns: Server health status information.
list_indexes
Retrieve a list of all indexes. Parameters: None. Returns: Array of indexes.
create_index
Create a new index. Parameters: uid (string, required), primary_key (string, optional). Returns: Creation task information.
get_documents
Retrieve documents from an index. Parameters: index_uid (string, required), limit (integer, optional), offset (integer, optional), fields (array of strings, optional). Returns: Array of documents.
add_documents
Add documents to an index. Parameters: index_uid (string, required), documents (array, required), primary_key (string, optional). Returns: Addition task information.
search
Search for documents in an index. Parameters: index_uid (string, required), query (string, required), limit (integer, optional), offset (integer, optional), filter (string, optional), sort (array of strings, optional). Returns: Search results.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"meilisearch": {
"env": {
"MEILISEARCH_HOST": "http://localhost:7700",
"MEILISEARCH_API_KEY": "api_key"
},
"args": [
"server",
"--no-logs",
"--log",
"path_to_log_file"
],
"command": "./bin/mcp-meilisearch"
}
}
}Linux
{
"env": {
"MEILISEARCH_HOST": "http://localhost:7700",
"MEILISEARCH_API_KEY": "api_key"
},
"args": [
"server",
"--no-logs",
"--log",
"path_to_log_file"
],
"command": "./bin/mcp-meilisearch"
}Macos
{
"env": {
"MEILISEARCH_HOST": "http://localhost:7700",
"MEILISEARCH_API_KEY": "api_key"
},
"args": [
"server",
"--no-logs",
"--log",
"path_to_log_file"
],
"command": "./bin/mcp-meilisearch"
}Windows
{
"env": {
"MEILISEARCH_HOST": "http://localhost:7700",
"MEILISEARCH_API_KEY": "api_key"
},
"args": [
"server",
"--no-logs",
"--log",
"path_to_log_file"
],
"command": "./bin/mcp-meilisearch"
}Meilisearch MCP Server (Go)
A Go-based wrapper for Meilisearch search engine that functions as a Model Context Protocol (MCP) server.
Overview
This project is a Go application designed to enable the Meilisearch search engine to be used as an MCP (Model Context Protocol) server. Through the MCP server, large language models (LLMs) like Claude can access Meilisearch's powerful search capabilities.
Features
- Lightweight and fast MCP server implemented in Go
- Seamless integration with Meilisearch API
- Interface compliant with the MCP protocol
- Support for key features including search, index management, and document operations
Installation
Prerequisites
- Go 1.24 or higher
- Running Meilisearch instance
Build Instructions
```bash
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
