ngram_extract
Extract and count n-grams (word or character level) from text.
This record as markdown: /tools/io-github-malamutemayhem-unclick-mcp-server/ngram-extract.md
What ngram_extract does on UnClick
AI agents call ngram_extract 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 |
|---|---|---|---|
n | number | — | N-gram size (default 2). |
top | number | — | Number of top entries to return (default 20). |
mode | string | — | 'word' (default) or 'character'. |
text | string | Yes | Text to analyse. |
Parameters from the server's own tool schema.
Why ngram_extract is rated Low
The tool performs text analysis by extracting linguistic patterns (n-grams) and counting their frequency. This is a read-only operation that retrieves information from provided text without creating, modifying, deleting, executing code, or affecting external systems. No reversible or irreversible changes occur.
From the tool's definition Tool description states 'Extract and count n-grams from text' — a pure data extraction and analysis operation with no side effects, modification, or external action.
Attacks that exploit this kind of access
The rule that runs ngram_extract 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 ngram_extract, this is the rule to start with:
ngram_extract 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 ngram_extract call is checked against it from then on.
Questions about ngram_extract
Extract and count n-grams (word or character level) from text. It is categorised as a Read tool in the UnClick MCP Server, which means it retrieves data without modifying state.
ngram_extract accepts 4 parameters: n, top, mode, text. Required: text. 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 ngram_extract: 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.
ngram_extract 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 ngram_extract 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 ngram_extract. 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.
ngram_extract 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