MeilisearchCAUTION
A Model Context Protocol (MCP) server for interacting with Meilisearch through LLM interfaces.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Meilisearch MCP Server
Meilisearch | Meilisearch Cloud | Documentation | Discord
⚡ Connect any LLM to Meilisearch and supercharge your AI with lightning-fast search capabilities! 🔍
🤔 What is this?
The Meilisearch MCP Server is a Model Context Protocol server that enables any MCP-compatible client (including Claude, OpenAI agents, and other LLMs) to interact with Meilisearch. This stdio-based server allows AI assistants to manage search indices, perform searches, and handle your data through natural conversation.
Why use this?
- 🤖 Universal Compatibility - Works with any MCP client, not just Claude
- 🗣️ Natural Language Control - Manage Meilisearch through conversation with any LLM
- 🚀
71ab62101abfOBSERVED · 2026-10-06Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add meilisearch-mcp --env MEILI_MASTER_KEY=${MEILI_MASTER_KEY} -- uvx meilisearch-mcp{
"mcpServers": {
"meilisearch-mcp": {
"command": "uvx",
"args": [
"meilisearch-mcp"
],
"env": {
"MEILI_MASTER_KEY": "${MEILI_MASTER_KEY}"
}
}
}
}Exposed tools (22)
15 read · 5 write · 2 destructive. Blast radius: 2 tools can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
add-documents | write | Add documents to an index |
cancel-tasks | read | Cancel tasks based on filters |
create-index | write | Create a new Meilisearch index |
create-key | write | Create a new API key |
delete-index | destructive | Delete a Meilisearch index |
delete-key | destructive | Delete an API key |
get-chat-workspace-settings | read | Get settings for a specific chat workspace |
get-connection-settings | read | Get current Meilisearch connection settings |
get-documents | read | Get documents from an index |
get-health-status | read | Get comprehensive health status of Meilisearch |
get-index-metrics | read | Get detailed metrics for an index |
get-keys | read | Get list of API keys |
get-settings | read | Get current settings for an index |
get-stats | read | Get database statistics |
get-system-info | read | Get system-level information |
get-task | read | Get information about a specific task |
get-version | read | Get Meilisearch version information |
health-check | read | Check Meilisearch server health |
list-indexes | read | List all Meilisearch indexes |
search | read | Search through Meilisearch indices. If indexUid is not provided, it will search across all indices. |
update-connection-settings | write | Update Meilisearch connection settings |
update-settings | write | Update settings for an index |
Trust audit
CAUTIONgrade B · trust 89/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- UNDECLARED (3 observation(s))
- Network
- declared (2 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (3)
rm -rf /var/lib/apt/lists/*
delete-index, delete-key
pytest, pytest-asyncio, black, mcp
Gates applied: no_behavioural_pass.
71ab62101abffull audit observations/trust-audit/mcp-server/meilisearch__meilisearch-2.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-06 | 71ab62101abf | CAUTION | B | 89 | first audit |
Questions
What is the Meilisearch MCP server?
A Model Context Protocol (MCP) server for interacting with Meilisearch through LLM interfaces.
What tools does Meilisearch expose?
22 in total: 15 read-only, 5 that write, and 2 that can delete or overwrite (delete-index, delete-key). Every one is listed on this page with its risk.
Is Meilisearch safe to connect to an agent?
With care. The audit graded it B (89/100) and found 3 things worth knowing before you trust this server, listed below with the exact line each was found on. Separately from the audit: 2 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does Meilisearch need?
It reads MEILI_MASTER_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Meilisearch run?
It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as meilisearch-mcp.
How current is this page?
The grade is for one exact copy of the source (71ab62101abf), read on 2026-10-06. The repository is watched and re-audited when it changes.