Keyword search across skill descriptions (from manifest) and global rule file contents. Args: - query (string): Search keyword or phrase - scope (
AI agents call rules_search to retrieve information from Claude Rules MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a search/query tool that retrieves information. It takes a keyword query and searches existing data (skill descriptions and rule files) but does not modify, delete, or execute anything. The scope argument (incomplete in the description but typical for search tools) likely filters which resources to search. No side effects are possible from searching text content.
From the tool's definition Tool performs 'keyword search across skill descriptions and global rule file contents' — a retrieval-only operation with no data modification or execution capabilities.
Attacks that exploit this kind of access
Keyword search across skill descriptions (from manifest) and global rule file contents. Args: - query (string): Search keyword or phrase - scope (. It is categorised as a Read tool in the Claude Rules MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Claude Rules MCP Server MCP server in PolicyLayer and add a rule for rules_search: 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 Claude Rules MCP Server. Nothing to install.
rules_search 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 rules_search 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 rules_search. 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.
rules_search is provided by the Claude Rules MCP Server MCP server (jeremykenedy/claude-rules-mcp-server). 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 →