Compatible with every major AI agent and IDE
What is the Meilisearch MCP Server?
Connect your Meilisearch instance to any AI agent to automate your search engine management and data indexing workflows.
What you can do
- Index Management — Create, list, update, and delete indexes. Perform atomic swaps between indexes for zero-downtime deployments.
- Document Operations — Add, update, or replace documents in bulk. Retrieve specific documents by ID or list them with advanced filtering and sorting.
- Granular Deletion — Remove documents individually, in batches, or by applying complex filter expressions to clean up your data.
- Metadata Inspection — Fetch detailed metadata for your indexes and documents to monitor your search engine's state.
How it works
- Subscribe to this server
- Enter your Meilisearch Instance URL and API Key
- Start managing your search data from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Developers — Index new data or debug search results directly from the code editor.
- Data Engineers — Automate index maintenance and document synchronization tasks.
- Content Managers — Quickly verify if specific content is correctly indexed without using a dedicated dashboard.
Built-in capabilities (44)
Add or replace documents in an index
Cancel pending or processing tasks
Request a chat completion from a workspace
Enable or disable experimental features
Trigger the creation of a Meilisearch dump
Create a new index
Create a new API key
Trigger the creation of a Meilisearch snapshot
Delete all documents in an index
Delete a single document
Delete multiple documents by ID
Delete documents matching a filter
Delete a dynamic search rule
Delete an index
Delete an API key
Delete finished tasks
Get details of a specific batch
Get a specific document by ID
Check the health of the Meilisearch instance
Get metadata for a specific index
Get stats of a specific index
Get details of a specific API key
Get all settings of an index
Get stats of all indexes and database size
Get details of a specific task
Get the version of the Meilisearch instance
List task batches
List chat workspaces
List documents in an index
List dynamic search rules for an index
List the status of experimental features
List all Meilisearch indexes
List API keys
List asynchronous tasks
Perform multiple search queries in a single call
Reset all settings of an index to defaults
Search for documents in an index
Create or update a dynamic search rule
Find documents similar to a given document ID
Swap multiple indexes atomically
Add or update documents (partial update)
Update an index primary key
Update an API key name or description
Update settings of an index
Why Claude Code?
Claude Code registers Meilisearch as an MCP server in a single terminal command. Once connected, Claude Code discovers all 44 tools at runtime and can call them headlessly. ideal for CI/CD pipelines, cron jobs, and automated workflows where Meilisearch data drives decisions without human intervention.
- —
Single-command setup:
claude mcp addregisters the server instantly. no config files to edit or applications to restart - —
Terminal-native workflow means MCP tools integrate seamlessly into shell scripts, CI/CD pipelines, and automated DevOps tasks
- —
Claude Code runs headlessly, enabling unattended batch processing using Meilisearch tools in cron jobs or deployment scripts
- —
Built by the same team that created the MCP protocol, ensuring first-class compatibility and the fastest adoption of new protocol features
Meilisearch in Claude Code
Meilisearch and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Meilisearch to Claude Code through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Meilisearch in Claude Code
The Meilisearch MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 44 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Claude Code only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Meilisearch for Claude Code
Every tool call from Claude Code to the Meilisearch MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I delete documents based on a specific condition or category?
Yes! You can use the delete_documents_by_filter tool. Just provide the index UID and a filter expression (e.g., 'category = electronics') to remove all matching documents at once.
How do I perform a zero-downtime index update?
You can use the swap_indexes tool. 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.
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.
How do I add an MCP server to Claude Code?
Run claude mcp add <name> --transport http "<url>" in your terminal. Claude Code registers the server and discovers all tools immediately.
Can Claude Code run MCP tools in headless mode?
Yes. Claude Code supports non-interactive execution, making it ideal for scripts, cron jobs, and CI/CD pipelines that need MCP tool access.
How do I list all connected MCP servers?
Run claude mcp in your terminal to see all registered servers and their status, or type /mcp inside an active Claude Code session.
Command not found: claude
Ensure Claude Code is installed globally: npm install -g @anthropic-ai/claude-code
Connection timeout
Check your internet connection and verify the Edge URL is reachable
Explore More MCP Servers
View all →
Open-Meteo Full Access
15 toolsThe ultimate weather Mega-Server: 15 tools covering forecast, historical (84 years), marine, air quality, pollen, climate projections (to 2100), flood, geocoding, and elevation — all in one zero-auth integration.

Wolfram Alpha
5 toolsSolve math, science, and engineering queries with computational intelligence.

Interest Amortization Engine
1 toolsGenerate exact SAC and Price (French) amortization schedules for real estate litigation.

Anthropic Alternative
6 toolsAccess Claude models via Anthropic API — send messages, count tokens, manage batches and discover models from any AI agent.
