模型上下文协议 - 使用 Claude desktop 与 Meilisearch 对话

# Using uv (recommended)
uv pip install meilisearch-mcp

# Using pip
pip install meilisearch-mcp

{
  "mcpServers": {
    "meilisearch": {
      "command": "uvx",
      "args": ["-n", "meilisearch-mcp"]
    }
  }

Please connect to my Meilisearch instance at MEILISEARCH_URL using the API key API_KEY

Can you check the connection to my Meilisearch instance and tell me what version it's running?

What indexes do I have in my Meilisearch instance?

Create a new index called "products" for our e-commerce site with the primary key "product_id"

How many documents are in my "products" index and what's its size?

Add these products to my "products" index:
[
  {"product_id": 1, "name": "Ergonomic Chair", "description": "Comfortable office chair", "price": 299.99, "category": "Furniture"},
  {"product_id": 2, "name": "Standing Desk", "description": "Adjustable height desk", "price": 499.99, "category": "Furniture"}
]

Add 10 documents in the index "products" with a name, category, price, and description of your choice

Show me the first 5 products in my "products" index

Update the ranking rules for the "products" index to prioritize word matches and handle typos, but make exact matches more important than proximity

Configure my "products" index to make the "name" and "description" fields searchable, but only "name", "price", and "category" should be displayed in results

Search the "products" index for "desk" and return the top 3 results

Search the "products" index for "chair" where the price is less than 200 and the category is "Furniture". Sort results by price in ascending order.

What are the current Meilisearch connection settings?

Run a health check on my Meilisearch instance

npx @modelcontextprotocol/inspector uvx -n meilisearch-mcp