Update index settings (ranking, faceting, etc.)
AI agents use update-settings to create or update resources in Meilisearch MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Meilisearch MCP Server environment.
This tool modifies index settings (ranking, faceting parameters) which affects index behavior and configuration. This is a Write operation—it creates or modifies data reversibly. It is not Destructive because settings can be reverted or updated again.
From the tool's definition Tool name 'update-settings' and description 'Update index settings (ranking, faceting, etc.)' indicate modification of search index configuration.
Documented attack patterns abuse exactly the kind of access update-settings gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Meilisearch MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for update-settings:
{
"version": "1",
"default": "deny",
"tools": {
"update-settings": {
"limits": [
{
"counter": "update-settings_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update-settings stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Update index settings (ranking, faceting, etc.). It is categorised as a Write tool in the Meilisearch MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Meilisearch MCP Server MCP server in PolicyLayer and add a rule for update-settings: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Meilisearch MCP Server. Nothing to install.
update-settings is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the update-settings rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for update-settings. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
update-settings is provided by the Meilisearch MCP Server MCP server (meilisearch/meilisearch-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Meilisearch MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
23 Meilisearch MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.