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 OpenAI Agents SDK?
The OpenAI Agents SDK auto-discovers all 44 tools from Meilisearch through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Meilisearch, another analyzes results, and a third generates reports, all orchestrated through Vinkius.
- —
Native MCP integration via
MCPServerSse, pass the URL and the SDK auto-discovers all tools with full type safety - —
Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure
- —
Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate
- —
First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output
Meilisearch in OpenAI Agents SDK
Meilisearch and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Meilisearch to OpenAI Agents SDK 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 OpenAI Agents SDK
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 OpenAI Agents SDK 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 OpenAI Agents SDK
Every tool call from OpenAI Agents SDK 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 does the OpenAI Agents SDK connect to MCP?
Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.
Can I use multiple MCP servers in one agent?
Yes. Pass a list of MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.
Does the SDK support streaming responses?
Yes. The SDK supports SSE and Streamable HTTP transports, both of which work natively with Vinkius.
MCPServerStreamableHttp not found
Ensure you have the latest version: pip install --upgrade openai-agents
Agent not calling tools
Make sure your prompt explicitly references the task the tools can help with.
Explore More MCP Servers
View all →
ElevenLabs
10 toolsGenerate high-quality AI speech via ElevenLabs — use lifelike voices, manage text-to-speech, track usage, and handle audio dubbing directly from any AI agent.

Gitpod
26 toolsAutomate cloud development environments — create, start, and manage Gitpod workspaces and organizations directly from any AI agent.

Clipboard History Searcher
1 toolsSearch through your exported clipboard history (Ditto, CopyQ, Maccy) with AI. Find that URL, phone number, or code snippet you copied days ago.

Genius
7 toolsSearch songs, get lyrics, annotations and artist info — the world's largest lyrics database.
