Create an index on a MongoDB collection
AI agents use mongo_create_index to create or update resources in Mcp Database — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Database environment.
Index creation is a structural modification that persists in the database, making it a Write operation rather than Read. It is not Destructive because indexes can be dropped without data loss, nor Execute because it doesn't run arbitrary code or shell commands. Severity is medium because index creation can impact query performance and resource usage if misapplied, but doesn't directly expose or delete data.
From the tool's definition Tool name 'mongo_create_index' and description 'Create an index on a MongoDB collection' indicate creation/modification of database metadata.
Attacks that exploit this kind of access
Create an index on a MongoDB collection. It is categorised as a Write tool in the Mcp Database MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Database MCP server in PolicyLayer and add a rule for mongo_create_index: 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 Mcp Database. Nothing to install.
mongo_create_index 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 mongo_create_index 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 mongo_create_index. 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.
mongo_create_index is provided by the Mcp Database MCP server (nam088/mcp-database-server). 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 →