AI agents call keyword_extract to retrieve information from Tools without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
lang | string | — | Language (default: zh) |
text | string | Yes | Text to extract keywords from (max 3000 chars) |
count | number | — | Number of keywords (1-20, default: 10) |
Parameters from the server's own tool schema.
This tool analyzes input text to identify and return keywords without creating, modifying, deleting, or executing anything. It is a pure read operation that queries/analyzes data and returns results. No data is written, destroyed, or executed. The potential for misuse is minimal—extracting keywords from text poses no security risk.
From the tool's definition Tool description states it 'Extract[s] keywords and key phrases from text' and 'Returns 10-20 keywords sorted by importance'. The verb 'extract' and 'returns' indicate data retrieval and analysis with no modification or side effects.
Attacks that exploit this kind of access
Extract keywords and key phrases from text with search intent classification. Returns 10-20 keywords sorted by importance with long-tail variations. It is categorised as a Read tool in the Tools MCP Server, which means it retrieves data without modifying state.
keyword_extract accepts 3 parameters: lang, text, count. Required: text. The full parameter table on this page comes from the server's own tool schema.
Register the Tools MCP server in PolicyLayer and add a rule for keyword_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 Tools. Nothing to install.
keyword_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 keyword_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 keyword_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.
keyword_extract is provided by the Tools MCP server (https://www.jiebang.site/mcp). 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 →