AI agents call sample to retrieve information from MongoDB MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves sample documents from a MongoDB collection without modifying, deleting, or executing arbitrary operations. It is a straightforward read operation with minimal blast radius—sampling cannot cause data loss or unintended writes. Confidence is high because the description and server context are clear and explicit about read-only semantics.
From the tool's definition Tool name 'sample' and description 'Get random sample documents from a collection' indicate read-only retrieval with no data modification. Server is explicitly described as 'read-only access to MongoDB databases'.
Documented attack patterns abuse exactly the kind of access sample gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MongoDB MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for sample:
{
"version": "1",
"default": "deny",
"tools": {
"sample": {}
}
}sample is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get random sample documents from a collection. It is categorised as a Read tool in the MongoDB MCP Server MCP Server, which means it retrieves data without modifying state.
Register the MongoDB MCP Server MCP server in PolicyLayer and add a rule for sample: 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 MongoDB MCP Server. Nothing to install.
sample 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 sample 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 sample. 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.
sample is provided by the MongoDB MCP Server MCP server (mongodb-developer/mongodb-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MongoDB 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.
3 MongoDB MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.