AI agents call search_hadith 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 is a data retrieval tool that searches and returns hadith records. The search modes (semantic, keyword, both) are all read-only operations that query existing data without modifying, deleting, or executing side effects. The sibling tools (fetch_hadith, list_collections, fetch_cross_references) reinforce that this server provides read-only access to a hadith corpus.
From the tool's definition Tool performs search operations across hadith texts with modes for semantic embeddings and keyword matching. Description indicates querying/retrieval only ('Search hadiths...uses embeddings...uses SQL LIKE').
Attacks that exploit this kind of access
Search hadiths: mode='semantic' (default) uses embeddings; keyword uses SQL LIKE; both runs both. 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 search_hadith: 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.
search_hadith 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 search_hadith 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 search_hadith. 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.
search_hadith 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 →