digest
AI agents call digest to retrieve information from Rozkoduj MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Given the server's focus on market analysis and natural language queries for trading insights, 'digest' most likely retrieves or summarizes market data without modifying it or executing trades. The empty description prevents higher confidence, but the name and sibling tools (analyze, buzz, calendar, etc.) all point toward Read operations. No evidence of side effects, financial commitments, or destructive actions.
From the tool's definition Tool name 'digest' combined with server purpose (market screening, analysis, scoring) suggests data retrieval/summarization. No description provided to confirm, reducing confidence.
Attacks that exploit this kind of access
digest. It is categorised as a Read tool in the Rozkoduj MCP MCP Server, which means it retrieves data without modifying state.
Register the Rozkoduj MCP server in PolicyLayer and add a rule for digest: 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 Rozkoduj MCP. Nothing to install.
digest 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 digest 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 digest. 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.
digest is provided by the Rozkoduj MCP server (rozkoduj/rozkoduj-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 →