AI agents call spreader_reflect to retrieve information from Cartridge without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool generates analytical prompts for the Reasoner vessel to examine loop patterns—a read-like operation that retrieves or produces data for analysis without causing side effects, data modification, or external execution. It fits the 'Read' category (search, list, get, fetch analogues) as it appears to produce reflective analysis output.
From the tool's definition Tool name 'spreader_reflect' with description stating it 'Generate[s] a reflection prompt' for analysis. The verb 'generate' combined with 'prompt' and 'analyze' indicates querying or producing introspective output about loop patterns, not modifying or…
Attacks that exploit this kind of access
Generate a reflection prompt for the Reasoner vessel to analyze loop patterns. It is categorised as a Read tool in the Cartridge MCP Server, which means it retrieves data without modifying state.
Register the Cartridge MCP server in PolicyLayer and add a rule for spreader_reflect: 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 Cartridge. Nothing to install.
spreader_reflect 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 spreader_reflect 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 spreader_reflect. 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.
spreader_reflect is provided by the Cartridge MCP server (lucineer/cartridge-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 →