Meilisearch MCP Server
Provides comprehensive tools for interacting with Meilisearch, including index management, document operations (add, update, delete), search capabilities with filters, settings configuration, task monitoring, and experimental vector search features.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Meilisearch MCP Server search for 'customer feedback' in the support tickets index"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Meilisearch MCP Server
A Model Context Protocol (MCP) server implementation for Meilisearch, enabling AI assistants to interact with Meilisearch through a standardized interface.
Features
Index Management: Create, update, and delete indexes
Document Management: Add, update, and delete documents
Search Capabilities: Perform searches with various parameters and filters
Settings Management: Configure index settings
Task Management: Monitor and manage asynchronous tasks
System Operations: Health checks, version information, and statistics
Vector Search: Experimental vector search capabilities
Installation
Installing via Smithery
To install Meilisearch MCP Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @devlimelabs/meilisearch-ts-mcp --client claudeManual Installation
Clone the repository:
git clone https://github.com/devlimelabs/meilisearch-ts-mcp.git cd meilisearch-ts-mcpInstall dependencies:
npm installCreate a
.envfile based on the example:cp .env.example .envEdit the
.envfile to configure your Meilisearch connection.
Docker Setup
The Meilisearch MCP Server can be run in a Docker container for easier deployment and isolation.
Using Docker Compose
The easiest way to get started with Docker is to use Docker Compose:
# Start the Meilisearch MCP Server
docker-compose up -d
# View logs
docker-compose logs -f
# Stop the server
docker-compose downBuilding and Running the Docker Image Manually
You can also build and run the Docker image manually:
# Build the Docker image
docker build -t meilisearch-ts-mcp .
# Run the container
docker run -p 3000:3000 --env-file .env meilisearch-ts-mcpDevelopment Setup
For developers who want to contribute to the Meilisearch MCP Server, we provide a convenient setup script:
# Clone the repository
git clone https://github.com/devlimelabs-ts-mcp/meilisearch-ts-mcp.git
cd meilisearch-ts-mcp
# Run the development setup script
./scripts/setup-dev.shThe setup script will:
Create a
.envfile from.env.exampleif it doesn't existInstall dependencies
Build the project
Run tests to ensure everything is working correctly
After running the setup script, you can start the server in development mode:
npm run devUsage
Building the Project
npm run buildRunning the Server
npm startDevelopment Mode
npm run devClaude Desktop Integration
The Meilisearch MCP Server can be integrated with Claude for Desktop, allowing you to interact with your Meilisearch instance directly through Claude.
Automated Setup
We provide a setup script that automatically configures Claude for Desktop to work with the Meilisearch MCP Server:
# First build the project
npm run build
# Then run the setup script
node scripts/claude-desktop-setup.jsThe script will:
Detect your operating system and locate the Claude for Desktop configuration file
Read your Meilisearch configuration from the
.envfileGenerate the necessary configuration for Claude for Desktop
Provide instructions for updating your Claude for Desktop configuration
Manual Setup
If you prefer to manually configure Claude for Desktop:
Locate your Claude for Desktop configuration file:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.jsonLinux:
~/.config/Claude/claude_desktop_config.json
Add the following configuration (adjust paths as needed):
{
"mcpServers": {
"meilisearch": {
"command": "node",
"args": ["/path/to/meilisearch-ts-mcp/dist/index.js"],
"env": {
"MEILISEARCH_HOST": "http://localhost:7700",
"MEILISEARCH_API_KEY": "your-api-key"
}
}
}
}Restart Claude for Desktop to apply the changes.
In Claude, type: "I want to use the Meilisearch MCP server" to activate the integration.
Cursor Integration
The Meilisearch MCP Server can also be integrated with Cursor, an AI-powered code editor.
Setting Up MCP in Cursor
Install and set up the Meilisearch MCP Server:
git clone https://github.com/devlimelabs/meilisearch-ts-mcp.git cd meilisearch-ts-mcp npm install npm run buildStart the MCP server:
npm startIn Cursor, open the Command Palette (Cmd/Ctrl+Shift+P) and search for "MCP: Connect to MCP Server".
Select "Connect to a local MCP server" and enter the following details:
Name: Meilisearch
Command: node
Arguments: /absolute/path/to/meilisearch-ts-mcp/dist/index.js
Environment Variables:
MEILISEARCH_HOST=http://localhost:7700 MEILISEARCH_API_KEY=your-api-key
Click "Connect" to establish the connection.
You can now interact with your Meilisearch instance through Cursor by typing commands like "Search my Meilisearch index for documents about..."
Available Tools
The Meilisearch MCP Server provides the following tools:
Index Tools
create-index: Create a new indexget-index: Get information about an indexlist-indexes: List all indexesupdate-index: Update an indexdelete-index: Delete an index
Document Tools
add-documents: Add documents to an indexget-document: Get a document by IDget-documents: Get multiple documentsupdate-documents: Update documentsdelete-document: Delete a document by IDdelete-documents: Delete multiple documentsdelete-all-documents: Delete all documents in an index
Search Tools
search: Search for documentsmulti-search: Perform multiple searches in a single request
Settings Tools
get-settings: Get index settingsupdate-settings: Update index settingsreset-settings: Reset index settings to defaultVarious specific settings tools (synonyms, stop words, ranking rules, etc.)
Task Tools
list-tasks: List tasks with optional filteringget-task: Get information about a specific taskcancel-tasks: Cancel tasks based on provided filterswait-for-task: Wait for a specific task to complete
System Tools
health: Check the health status of the Meilisearch serverversion: Get version informationinfo: Get system informationstats: Get statistics about indexes
Vector Tools (Experimental)
enable-vector-search: Enable vector searchget-experimental-features: Get experimental features statusupdate-embedders: Configure embeddersget-embedders: Get embedders configurationreset-embedders: Reset embedders configurationvector-search: Perform vector search
License
MIT
Available Tools
68 toolsadd-documentsC
Add documents to a Meilisearch index
Inputs: indexUid (required), documents (required), primaryKey.
cancel-tasksC
Cancel tasks based on provided filters
Inputs: statuses, types, indexUids, uids.
create-indexC
Create a new Meilisearch index
Inputs: indexUid (required), primaryKey.
delete-all-documentsC
Delete all documents in a Meilisearch index
Inputs: indexUid (required).
delete-documentC
Delete a document by its ID from a Meilisearch index
Inputs: indexUid (required), documentId (required).
delete-documentsB
Delete multiple documents by their IDs from a Meilisearch index
Inputs: indexUid (required), documentIds (required).
delete-indexC
Delete a Meilisearch index
Inputs: indexUid (required).
delete-tasksC
Delete tasks based on provided filters
Inputs: statuses, types, indexUids, uids, +4 more.
enable-vector-searchB
Enable the vector search experimental feature in Meilisearch
Inputs: no named parameters.
facet-searchC
Search for facet values matching specific criteria
Inputs: indexUid (required), facetName (required), facetQuery, filter.
get-displayed-attributesC
Get the displayed attributes setting
Inputs: indexUid (required).
get-distinct-attributeC
Get the distinct attribute setting
Inputs: indexUid (required).
get-documentC
Get a document by its ID from a Meilisearch index
Inputs: indexUid (required), documentId (required), fields.
get-documentsC
Get documents from a Meilisearch index
Inputs: indexUid (required), limit, offset, fields, +1 more.
get-embeddersC
Get the embedders configuration for an index
Inputs: indexUid (required).
get-experimental-featuresB
Get the status of experimental features in Meilisearch
Inputs: no named parameters.
get-facetingC
Get the faceting setting
Inputs: indexUid (required).
get-filterable-attributesC
Get the filterable attributes setting
Inputs: indexUid (required).
get-indexC
Get information about a specific Meilisearch index
Inputs: indexUid (required).
get-paginationC
Get the pagination setting
Inputs: indexUid (required).
get-ranking-rulesC
Get the ranking rules setting
Inputs: indexUid (required).
get-searchable-attributesC
Get the searchable attributes setting
Inputs: indexUid (required).
get-settingsC
Get all settings for a Meilisearch index
Inputs: indexUid (required).
get-sortable-attributesC
Get the sortable attributes setting
Inputs: indexUid (required).
get-stop-wordsC
Get the stop words setting
Inputs: indexUid (required).
get-synonymsC
Get the synonyms setting
Inputs: indexUid (required).
get-taskC
Get information about a specific task
Inputs: taskUid (required).
get-tasksC
Get information about tasks with optional filtering
Inputs: limit, from, status, type, +1 more.
get-typo-toleranceC
Get the typo tolerance setting
Inputs: indexUid (required).
healthA
Check if the Meilisearch server is healthy
Inputs: no named parameters.
infoB
Get the system information of the Meilisearch server
Inputs: no named parameters.
list-indexesB
List all indexes in the Meilisearch instance
Inputs: limit, offset.
list-tasksC
List tasks with optional filtering
Inputs: limit, from, statuses, types, +2 more.
multi-searchC
Perform multiple searches in one request
Inputs: searches (required).
reset-displayed-attributesB
Reset the displayed attributes setting to its default value
Inputs: indexUid (required).
reset-distinct-attributeC
Reset the distinct attribute setting to its default value
Inputs: indexUid (required).
reset-embeddersC
Reset the embedders configuration for an index
Inputs: indexUid (required).
reset-facetingC
Reset the faceting setting to its default value
Inputs: indexUid (required).
reset-filterable-attributesC
Reset the filterable attributes setting to its default value
Inputs: indexUid (required).
reset-paginationC
Reset the pagination setting to its default value
Inputs: indexUid (required).
reset-ranking-rulesC
Reset the ranking rules setting to its default value
Inputs: indexUid (required).
reset-searchable-attributesC
Reset the searchable attributes setting to its default value
Inputs: indexUid (required).
reset-settingsB
Reset all settings for a Meilisearch index to their default values
Inputs: indexUid (required).
reset-sortable-attributesB
Reset the sortable attributes setting to its default value
Inputs: indexUid (required).
reset-stop-wordsC
Reset the stop words setting to its default value
Inputs: indexUid (required).
reset-synonymsC
Reset the synonyms setting to its default value
Inputs: indexUid (required).
reset-typo-toleranceB
Reset the typo tolerance setting to its default value
Inputs: indexUid (required).
searchC
Search for documents in a Meilisearch index
Inputs: indexUid (required), q (required), limit, offset, +11 more.
statsB
Get statistics about all indexes or a specific index
Inputs: indexUid.
swap-indexesC
Swap two or more indexes in Meilisearch
Inputs: indexes (required).
update-displayed-attributesC
Update the displayed attributes setting
Inputs: indexUid (required), value (required).
update-distinct-attributeC
Update the distinct attribute setting
Inputs: indexUid (required), value (required).
update-documentsC
Update documents in a Meilisearch index
Inputs: indexUid (required), documents (required), primaryKey.
update-embeddersC
Configure embedders for vector search
Inputs: indexUid (required), embedders (required).
update-facetingC
Update the faceting setting
Inputs: indexUid (required), value (required).
update-filterable-attributesC
Update the filterable attributes setting
Inputs: indexUid (required), value (required).
update-indexC
Update a Meilisearch index (currently only supports updating the primary key)
Inputs: indexUid (required), primaryKey (required).
update-paginationC
Update the pagination setting
Inputs: indexUid (required), value (required).
update-ranking-rulesC
Update the ranking rules setting
Inputs: indexUid (required), value (required).
update-searchable-attributesC
Update the searchable attributes setting
Inputs: indexUid (required), value (required).
update-settingsC
Update settings for a Meilisearch index
Inputs: indexUid (required), settings (required).
update-sortable-attributesC
Update the sortable attributes setting
Inputs: indexUid (required), value (required).
update-stop-wordsC
Update the stop words setting
Inputs: indexUid (required), value (required).
update-synonymsC
Update the synonyms setting
Inputs: indexUid (required), value (required).
update-typo-toleranceC
Update the typo tolerance setting
Inputs: indexUid (required), value (required).
vector-searchC
Perform a vector search in a Meilisearch index
Inputs: indexUid (required), vector (required), limit, offset, +6 more.
versionA
Get the version information of the Meilisearch server
Inputs: no named parameters.
wait-for-taskC
Wait for a specific task to complete
Inputs: taskUid (required), timeoutMs, intervalMs.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 68 tools
Most tools have distinct purposes targeting specific resources and actions, such as 'add-documents' vs. 'update-documents' or 'get-document' vs. 'delete-document'. However, there is some overlap between 'list-tasks' and 'get-tasks', which could cause confusion as they both retrieve task information with filtering, though descriptions help clarify their differences.
Tool names follow a highly consistent verb-noun pattern throughout, using kebab-case (e.g., 'create-index', 'get-settings', 'reset-ranking-rules'). This predictability makes it easy for agents to understand and select tools based on their naming conventions without ambiguity.
With 68 tools, the count is excessive for the Meilisearch domain, making the surface heavy and potentially overwhelming. While Meilisearch has many features, this high number suggests over-fragmentation, such as separate tools for each setting reset (e.g., 'reset-displayed-attributes', 'reset-searchable-attributes'), which could be consolidated.
The tool set provides comprehensive coverage of Meilisearch's core functionalities, including CRUD operations for documents and indexes, task management, search capabilities (standard, facet, vector, multi-search), settings management (get, update, reset for all attributes), and system operations (health, info, version). No obvious gaps are present for the domain.
Related MCP Connectors
Search multiple indices, index data, and get personalized recommendations
Complete SEO and AI Search stack for your AI agents
Ingest, manage, and retrieve documents for RAG-powered AI applications
Versioned documentation registry and semantic search for AI tools and coding assistants.