Use this when the signed-in user asks about words they've gotten wrong, missed words, words to review, or wants to revisit recent mistakes. Returns up to 25 words from the last N days (default 7) with miss-rate and last-seen timestamp, plus a link to the in-app Recent Mistakes page. SUMMARISE — n...
Risk signalsBulk/mass operation — affects multiple targets
Part of the Vocab Voyage server.
Free to start. No card required.
AI agents call get_recent_mistakes to retrieve information from Vocab Voyage without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though get_recent_mistakes only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"get_recent_mistakes": {}
}
}See the full Vocab Voyage policy for all 31 tools.
These attack patterns abuse exactly the kind of access get_recent_mistakes gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Use this when the signed-in user asks about words they've gotten wrong, missed words, words to review, or wants to revisit recent mistakes. Returns up to 25 words from the last N days (default 7) with miss-rate and last-seen timestamp, plus a link to the in-app Recent Mistakes page. SUMMARISE — never dump every row; tell the user the count, name 2–3 sample words, and recommend the page URL. Requires sign-in.. It is categorised as a Read tool in the Vocab Voyage MCP Server, which means it retrieves data without modifying state.
Register the Vocab Voyage MCP server in PolicyLayer and add a rule for get_recent_mistakes: 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 Vocab Voyage. Nothing to install.
get_recent_mistakes 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_recent_mistakes 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_recent_mistakes. 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_recent_mistakes is provided by the Vocab Voyage MCP server (https://gponcrussdahcdyrlhcr.supabase.co/functions/v1/mcp-server?ref=mcp_registry). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 31 Vocab Voyage tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.