Related-word lookup via Datamuse. Supply a seed word and relation kind: rhymes, near-rhymes, synonyms, antonyms, means (semantic match), triggers, homophones, sounds-like, spelled-like, follows-from, preceded-by. Returns ranked candidates with relevance score, syllable count, and grammar tags.
AI agents call word.related 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 is a straightforward read operation that queries an external word relationship database and returns information. It retrieves data based on input parameters (seed word and relation kind) without creating, modifying, deleting, or executing any code. The pay-per-call nature via x402 affects billing but does not change the risk classification of the tool's action itself.
From the tool's definition Tool performs a lookup operation ('Related-word lookup via Datamuse') that returns data (ranked candidates with relevance scores, syllable counts, grammar tags) with no modification or deletion of data and no side effects.
Attacks that exploit this kind of access
Related-word lookup via Datamuse. Supply a seed word and relation kind: rhymes, near-rhymes, synonyms, antonyms, means (semantic match), triggers, homophones, sounds-like, spelled-like, follows-from, preceded-by. Returns ranked candidates with relevance score, syllable count, and grammar tags. 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.related: 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.related 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.related 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.related. 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.related 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 →