Generate a wordlist from a corpus
AI agents call get_wordlist to retrieve information from Sketch Engine MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves linguistic data (a wordlist) from a corpus without creating, modifying, deleting, executing code, or committing financial transactions. It is a straightforward data retrieval operation consistent with other Read-category tools on this server (get_collocations, get_concordance, get_corpora, get_corpus_info, etc.).
From the tool's definition Tool name is 'get_wordlist' and description states 'Generate a wordlist from a corpus' — a read-only retrieval operation that queries corpus data without modification.
Attacks that exploit this kind of access
Generate a wordlist from a corpus. It is categorised as a Read tool in the Sketch Engine MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Sketch Engine MCP Server MCP server in PolicyLayer and add a rule for get_wordlist: 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 Sketch Engine MCP Server. Nothing to install.
get_wordlist 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 get_wordlist 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 get_wordlist. 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.
get_wordlist is provided by the Sketch Engine MCP Server MCP server (riccap/sketch-engine-mcp-server). 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 →