AI agents call fetch_cross_references to retrieve information from Hadith without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only query operation that retrieves data (cross-reference matches) without creating, modifying, deleting, or executing any side effects. It is a data retrieval operation consistent with the Read category.
From the tool's definition The tool 'fetch_cross_references' fetches and returns similarity matches across hadith collections. The description states it retrieves 'cross-collection similarity matches' with no mention of modification, deletion, or execution of external operations.
Attacks that exploit this kind of access
Cross-collection similarity matches for a hadith (by hadith_id or collection + number). It is categorised as a Read tool in the Hadith MCP Server, which means it retrieves data without modifying state.
Register the Hadith MCP server in PolicyLayer and add a rule for fetch_cross_references: 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 Hadith. Nothing to install.
fetch_cross_references 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 fetch_cross_references 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 fetch_cross_references. 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.
fetch_cross_references is provided by the Hadith MCP server (ovehbe/hadith-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 →