AI agents call word.define to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool purely retrieves and queries public dictionary data without side effects. It is a straightforward Read operation analogous to a lookup or fetch. No data is created, modified, deleted, or executed. The pay-per-call settlement model does not change the tool's functional category—the tool itself does not move funds or commit financial obligations on its own.
From the tool's definition Tool 'word.define' returns dictionary data including 'IPA phonetic transcription(s), audio URLs, and meanings grouped by part of speech with definitions, examples, synonyms, antonyms' from dictionaryapi.dev.
Attacks that exploit this kind of access
English dictionary entry via dictionaryapi.dev (Wiktionary, CC BY-SA). Returns IPA phonetic transcription(s), audio URLs, and meanings grouped by part of speech with definitions, examples, synonyms, antonyms. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for word.define: 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 Mcp. Nothing to install.
word.define 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 word.define 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 word.define. 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.
word.define is provided by the MCP server (@2sio/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 →