An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Meilisearch to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Run your search engine operations through your AI agent.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 44 capabilities

We ship only the actions that matter.

Capability set01 / 11

01-04

4 capabilities in this set.

Part of 44 available through Meilisearch.

  1. 01

    Update key

    This capability updates the name or description of an existing API key.

  2. 02

    Create dump

    Use this to trigger a Meilisearch dump for data backup.

  3. 03

    Cancel tasks

    This capability stops any pending or currently processing tasks.

  4. 04

    Configure experimental features

    Toggle experimental features on or off for your instance.

Capability set02 / 11

05-08

4 capabilities in this set.

Part of 44 available through Meilisearch.

  1. 05

    Create index

    This capability creates a brand new index in your Meilisearch instance.

  2. 06

    Create snapshot

    Trigger a snapshot of your current data state.

  3. 07

    Delete all documents

    This capability wipes every document from a specific index.

  4. 08

    Delete document

    Use this to remove a single document by its ID.

Capability set03 / 11

09-12

4 capabilities in this set.

Part of 44 available through Meilisearch.

  1. 09

    Delete documents batch

    This capability deletes a group of documents using their IDs.

  2. 10

    Delete documents by filter

    Remove documents that match a specific filter expression.

  3. 11

    Delete dynamic search rule

    This capability removes a specific dynamic search rule.

  4. 12

    Delete index

    Use this to completely remove an index.

Capability set04 / 11

13-16

4 capabilities in this set.

Part of 44 available through Meilisearch.

  1. 13

    Delete tasks

    This capability clears out finished tasks from your history.

  2. 14

    Get batch

    Retrieve the specific details of a task batch.

  3. 15

    Get health

    Check if your Meilisearch instance is running correctly.

  4. 16

    Get index

    Fetch metadata for a specific index.

Capability set05 / 11

17-20

4 capabilities in this set.

Part of 44 available through Meilisearch.

  1. 17

    Get index stats

    Get detailed statistics for a single index.

  2. 18

    Get key

    Retrieve details for a specific API key.

  3. 19

    Get settings

    Fetch all current settings for an index.

  4. 20

    Get stats

    Get a high level view of all indexes and the total database size.

Capability set06 / 11

21-24

4 capabilities in this set.

Part of 44 available through Meilisearch.

  1. 21

    List batches

    This capability provides a list of all task batches.

  2. 22

    List chats

    Retrieve a list of available chat workspaces.

  3. 23

    List dynamic search rules

    List the dynamic search rules currently applied to an index.

  4. 24

    List experimental features

    Check the status of all experimental features.

Capability set07 / 11

25-28

4 capabilities in this set.

Part of 44 available through Meilisearch.

  1. 25

    List indexes

    Get a list of every index in your instance.

  2. 26

    List keys

    Retrieve a list of all configured API keys.

  3. 27

    Reset settings

    Revert an index's settings back to their default state.

  4. 28

    Set dynamic search rule

    Create or update a rule for dynamic searching.

Capability set08 / 11

29-32

4 capabilities in this set.

Part of 44 available through Meilisearch.

  1. 29

    Update index

    Change the primary key for a specific index.

  2. 30

    Add documents

    Add new documents or replace existing ones in an index.

  3. 31

    Chat completion

    Request a chat completion from a workspace.

  4. 32

    Create key

    Generate a new API key for your instance.

Capability set09 / 11

33-36

4 capabilities in this set.

Part of 44 available through Meilisearch.

  1. 33

    Delete key

    Remove an existing API key.

  2. 34

    Get document

    Retrieve a single document using its ID.

  3. 35

    Get task

    Fetch the details of a specific task.

  4. 36

    Get version

    Check which version of Meilisearch you are running.

Capability set10 / 11

37-40

4 capabilities in this set.

Part of 44 available through Meilisearch.

  1. 37

    List documents

    Get a list of documents within an index.

  2. 38

    List tasks

    List all asynchronous tasks currently in the system.

  3. 39

    Multi search

    Run multiple search queries in one single call.

  4. 40

    Search documents

    Execute a search query against an index.

Capability set11 / 11

41-44

4 capabilities in this set.

Part of 44 available through Meilisearch.

  1. 41

    Similar documents

    Find documents that are similar to a specific ID.

  2. 42

    Swap indexes

    Perform an atomic swap between multiple indexes.

  3. 43

    Update documents

    Perform a partial update on existing documents.

  4. 44

    Update settings

    Modify the settings for a specific index.

Real work

What teams actually run

01

Automated Data Sync

Tell your agent to push a new batch of JSON data into a specific index after a database migration.

02

Rapid Debugging

Ask your agent to find a specific document by ID to verify why a search result is missing.

03

Index Maintenance

Use the agent to clear out old documents using a filter once they expire.

04

System Health Checks

Ask your agent to check the health of the instance during a deployment.

Automate a task

Put Meilisearch to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Meilisearch works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put Meilisearch to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

1401ms average. Fast in production.

Meilisearch is checked daily against the live service.

Daily averagePeak 1650ms
Oct 3Today
Fastest day
1138ms
Slowest day
1650ms
14-day trend
Slowing+5%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 44 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Meilisearch, so you can see the experience inside your AI.

It does not authenticate your account with Meilisearch. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Meilisearch Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_zvxhlZ8xtjn1uMtmbqWfMxBRRJBkYtadvczmRQ3Q/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Meilisearch capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "meilisearch-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_zvxhlZ8xtjn1uMtmbqWfMxBRRJBkYtadvczmRQ3Q/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Meilisearch in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Meilisearch owners hand off.

This MCP is built for technical users who need to interact with search data without leaving their development environment.

  • 01

    Developers

    They use the agent to index new data or debug search results directly in their editor.

  • 02

    Data Engineers

    They hand off index maintenance and document synchronization tasks to the agent.

  • 03

    Content Managers

    They use the agent to verify if specific content is correctly indexed.

FAQ

Questions Meilisearch owners ask.

  • 01

    How do I connect my Meilisearch instance?

    You just need to provide your Meilisearch Instance URL and your API Key in the Vinkius setup. Once connected, it is available in your AI client.

  • 02

    Can I perform bulk updates through the AI?

    Yes, you can use the add_documents capability to add or replace multiple documents at once.

  • 03

    Is it safe to manage API keys through this MCP?

    Yes, the MCP includes capabilities to create, list, and delete API keys to manage your instance security.

  • 04

    Can I cancel a long running task?

    Yes, you can use the cancel_tasks capability to stop pending or processing tasks.

  • 05

    Does this support zero-downtime deployments?

    Yes, you can use the swap_indexes capability to perform atomic swaps between indexes.

  • 06

    Can I delete documents based on a specific condition or category?

    Yes! You can use the delete_documents_by_filter capability. Just provide the index UID and a filter expression (e.g., 'category = electronics') to remove all matching documents at once.

  • 07

    How do I perform a zero-downtime index update?

    You can use the swap_indexes capability. This allows you to swap the names of two or more indexes atomically, ensuring your search remains active while you switch to a newly populated index.

  • 08

    Is it possible to retrieve only specific fields from a document?

    Absolutely. When using get_document or list_documents, you can provide a comma-separated list of fields to return, reducing the payload size and focusing on the data you need.

Explore

More in Loved By Devs

Suggestions

Connect Meilisearch to Claude, Cursor, ChatGPT & more