AI agents call filter_spells_by_level 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.
This tool filters spell information by game mechanic level—a pure read operation against static game reference material. No side effects, no data modification, no code execution, no financial impact. Consistent with other reference-lookup tools on this D&D knowledge server.
From the tool's definition Tool name 'filter_spells_by_level' indicates a query/filtering operation on spell data. All sibling tools (find_monsters_by_challenge_rating, get_class, get_spell, list_monster_types, etc.) are read-only lookups against D&D 5e reference data.
Documented attack patterns abuse exactly the kind of access filter_spells_by_level 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 filter_spells_by_level:
{
"version": "1",
"default": "deny",
"tools": {
"filter_spells_by_level": {}
}
} filter_spells_by_level 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.
filter_spells_by_level. 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 filter_spells_by_level: 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.
filter_spells_by_level 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 filter_spells_by_level 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 filter_spells_by_level. 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.
filter_spells_by_level 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.