bloom_filter
Build a Bloom filter from items and test membership of query items (probabilistic, no false negatives).
This record as markdown: /tools/io-github-malamutemayhem-unclick-mcp-server/bloom-filter.md
What bloom_filter does on UnClick
AI agents invoke bloom_filter to trigger actions in UnClick. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
| Parameter | Type | Required | Description |
|---|---|---|---|
items | array | Yes | Strings to insert into the filter |
query | array | Yes | Strings to check for membership |
fp_rate | number | — | Target false positive rate (default 0.01) |
Parameters from the server's own tool schema.
Why bloom_filter is rated High
The tool performs a computational operation — constructing a probabilistic data structure (Bloom filter) and running membership queries against it. It doesn't simply retrieve existing data (it builds something), nor does it write persistent data, delete anything, or involve financial transactions. It falls under Execute as it runs an algorithmic computation on provided inputs.
From the tool's definition 'Build a Bloom filter from items and test membership of query items (probabilistic, no false negatives)'
Attacks that exploit this kind of access
The rule that runs bloom_filter 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 bloom_filter, this is the rule to start with:
bloom_filter stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. 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 bloom_filter call is checked against it from then on.
Questions about bloom_filter
Build a Bloom filter from items and test membership of query items (probabilistic, no false negatives). It is categorised as a Execute tool in the UnClick MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
bloom_filter accepts 3 parameters: items, query, fp_rate. Required: items, query. 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 bloom_filter: 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.
bloom_filter is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the bloom_filter 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 bloom_filter. 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.
bloom_filter 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.
Across the catalogue