AI agents call expand_context 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.
Despite the empty description lowering confidence slightly, the tool operates within a read-only biblical search and retrieval system. The sibling tools all perform information retrieval without side effects, and 'expand_context' appears consistent with this pattern—likely returning additional related passage context or metadata rather than modifying, deleting, or executing arbitrary code.
From the tool's definition Tool belongs to a Bible MCP server focused on 'semantic search and retrieval' with sibling tools like 'search_bible', 'lookup_passage', 'get_entity_passages', and 'summarize_passage' that are all read-only retrieval operations.
Attacks that exploit this kind of access
expand_context. 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 expand_context: 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.
expand_context 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 expand_context 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 expand_context. 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.
expand_context 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 →