AI agents call lookup_passage to retrieve information from Bible MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool's name 'lookup_passage' and its position among sibling read-only retrieval tools (search_bible, get_entity_passages, expand_context) strongly suggests it retrieves or queries biblical passages without modification. No mechanism for creating, deleting, or executing code is implied. The empty description slightly reduces confidence, but the semantic context is clear.
From the tool's definition Tool name 'lookup_passage' paired with server's documented functions including 'search_bible', 'get_entity_passages', and 'expand_context' all perform retrieval operations.
Attacks that exploit this kind of access
lookup_passage. It is categorised as a Read tool in the Bible MCP MCP Server, which means it retrieves data without modifying state.
Register the Bible MCP server in PolicyLayer and add a rule for lookup_passage: 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 Bible MCP. Nothing to install.
lookup_passage 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 lookup_passage 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 lookup_passage. 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.
lookup_passage is provided by the Bible MCP server (parsifal295/bible-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 →