Returns the full skills-manifest.json — names and descriptions for all 484 skills plus 17 global rule names. Use this first to discover what is available before fetching individual skills or rules. Returns structured JSON: { total_skills, total_rules, skills[], rules[] }
AI agents call rules_get_manifest 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 tool performs a query/lookup operation that retrieves structured information about available skills and rules. It has no side effects—it does not modify, delete, execute, or move anything. The returned data is reference information to enable discovery. This is a pure Read operation with low blast radius if misused by an AI agent.
From the tool's definition Tool description states it 'Returns the full skills-manifest.json' and 'discover what is available before fetching individual skills or rules.' The action is retrieval of metadata with no modification, deletion, or execution capability.
Attacks that exploit this kind of access
Returns the full skills-manifest.json — names and descriptions for all 484 skills plus 17 global rule names. Use this first to discover what is available before fetching individual skills or rules. Returns structured JSON: { total_skills, total_rules, skills[], rules[] }. 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_get_manifest: 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_get_manifest 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_get_manifest 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_get_manifest. 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_get_manifest 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 →