search_rules
AI agents call search_rules to retrieve information from Remote MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
In the context of this server (appears to be a game/tabletop RPG reference system), 'search_rules' most likely retrieves rule information without modifying data. No evidence suggests code execution, data modification, or destructive operations. Confidence is slightly reduced due to the empty description, but the sibling tool patterns support a Read classification.
From the tool's definition Tool name 'search_rules' suggests querying or retrieving rules information. The description is empty, which prevents definitive categorization, but the name pattern aligns with read operations (similar to sibling tools: get_class_details, get_entry,…
Attacks that exploit this kind of access
search_rules. It is categorised as a Read tool in the Remote MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Remote MCP Server MCP server in PolicyLayer and add a rule for search_rules: 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 Remote MCP Server. Nothing to install.
search_rules 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_rules 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_rules. 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_rules is provided by the Remote MCP Server MCP server (robertsapunarich/mcp-ose). 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 →