AI agents call search_api to retrieve information from D&D Knowledge Navigator without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The search_api tool performs information retrieval from a static D&D knowledge database. No evidence suggests it creates, modifies, deletes, executes code, or initiates financial transactions. The consistent pattern of read-only query tools across the server confirms this is a data retrieval interface with no side effects or destructive capabilities.
From the tool's definition Tool is named 'search_api' with description 'Search the D&D API for specific content' and is part of a server providing read-only queries to D&D 5e game information.
Documented attack patterns abuse exactly the kind of access search_api gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and D&D Knowledge Navigator, and nothing reaches the server without passing your rules. This is the rule we recommend for search_api:
{
"version": "1",
"default": "deny",
"tools": {
"search_api": {}
}
}search_api is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Search the D&D API for specific content. It is categorised as a Read tool in the D&D Knowledge Navigator MCP Server, which means it retrieves data without modifying state.
Register the D&D Knowledge Navigator MCP server in PolicyLayer and add a rule for search_api: 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 D&D Knowledge Navigator. Nothing to install.
search_api 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_api 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_api. 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_api is provided by the D&D Knowledge Navigator MCP server (procload/dnd-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 14 D&D Knowledge Navigator tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
14 D&D Knowledge Navigator tools catalogued and risk-classified — across an index of 42,500+ MCP servers.