Retrieves the names of all indexes
AI agents call list_index_names to retrieve information from Azure Ai Search Python Preview without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only fetches and returns index names, which is a read-only operation with no side effects. It has minimal security risk as it merely enumerates available indexes. Even if an AI agent calls this repeatedly or in unexpected ways, no data is modified, deleted, or moved, and no code is executed.
From the tool's definition 'Retrieves the names of all indexes' - this is a query operation that returns metadata about available search indexes without modifying any data.
Attacks that exploit this kind of access
Retrieves the names of all indexes. It is categorised as a Read tool in the Azure Ai Search Python Preview MCP Server, which means it retrieves data without modifying state.
Register the Azure Ai Search Python Preview MCP server in PolicyLayer and add a rule for list_index_names: 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 Azure Ai Search Python Preview. Nothing to install.
list_index_names is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_index_names 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 list_index_names. 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.
list_index_names is provided by the Azure Ai Search Python Preview MCP server (projectacetylcholine/mcp-server-azure-ai-search-python-preview). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →