get_shabbat_times
AI agents call get_shabbat_times to retrieve information from Hebcal MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries a Jewish calendar API to retrieve Shabbat timing information for users. It reads and returns data without modifying, deleting, or executing external operations. The empty description is compensated by the clear naming convention and consistent context from sibling tools on the same server, all of which are read-only calendar queries.
From the tool's definition Tool name 'get_shabbat_times' and server description indicate retrieval of Shabbat candle lighting and Havdalah times.
Attacks that exploit this kind of access
get_shabbat_times. It is categorised as a Read tool in the Hebcal MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Hebcal MCP Server MCP server in PolicyLayer and add a rule for get_shabbat_times: 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 Hebcal MCP Server. Nothing to install.
get_shabbat_times 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_shabbat_times 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_shabbat_times. 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_shabbat_times is provided by the Hebcal MCP Server MCP server (shaymc3/hebcal-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 →