AI agents call search_spellbook to retrieve information from Dune without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs read-only discovery of data schema definitions from GitHub Spellbook. It returns informational metadata about available tables and their structure ('zero-credit schema discovery') with no capability to modify, delete, or execute operations. It is purely informational retrieval, fitting the 'Read' category with low severity since it has no side effects and limited blast radius.
From the tool's definition 'Search GitHub Spellbook for official tables (.sql/.yml). Zero-credit schema discovery.' — the tool retrieves and queries table schema metadata from an external repository without modifying data or executing queries.
Attacks that exploit this kind of access
Search GitHub Spellbook for official tables (.sql/.yml). Zero-credit schema discovery. It is categorised as a Read tool in the Dune MCP Server, which means it retrieves data without modifying state.
Register the Dune MCP server in PolicyLayer and add a rule for search_spellbook: 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 Dune. Nothing to install.
search_spellbook 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_spellbook 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_spellbook. 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_spellbook is provided by the Dune MCP server (nice-bills/dune-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 →