reservoir_sample
Select k random items from a list with equal probability using reservoir sampling.
This record as markdown: /tools/io-github-malamutemayhem-unclick-mcp-server/reservoir-sample.md
What reservoir_sample does on UnClick
AI agents call reservoir_sample to retrieve information from UnClick without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
k | number | — | Number of items to sample (default 1) |
seed | number | — | Optional seed for reproducible results |
items | array | Yes | Array of items to sample from |
Parameters from the server's own tool schema.
Why reservoir_sample is rated Low
This is a statistical sampling utility that reads from an input list and returns a subset. No data is modified, deleted, written to external systems, or executed. The operation is deterministic and reversible (rerun to get a different sample). Classification as Read is appropriate for query/retrieval operations with no side effects.
From the tool's definition Tool 'reservoir_sample' performs random selection from a list ("Select k random items") without modifying data or triggering external operations. The operation is purely computational and returns a subset of provided items with no side effects.
Attacks that exploit this kind of access
The rule that runs reservoir_sample safely
PolicyLayer is an MCP gateway: it sits between your AI agents and UnClick, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For reservoir_sample, this is the rule to start with:
reservoir_sample is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect UnClick, apply this rule, and every reservoir_sample call is checked against it from then on.
Questions about reservoir_sample
Select k random items from a list with equal probability using reservoir sampling. It is categorised as a Read tool in the UnClick MCP Server, which means it retrieves data without modifying state.
reservoir_sample accepts 3 parameters: k, seed, items. Required: items. The full parameter table on this page comes from the server's own tool schema.
Register the UnClick MCP server in PolicyLayer and add a rule for reservoir_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 UnClick. Nothing to install.
reservoir_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 reservoir_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 reservoir_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.
reservoir_sample is provided by the UnClick MCP server (@unclick/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on UnClick, and thousands of servers like it.
This server
Across the catalogue