Algorithmic behavior analysis (no LLM). Returns healthScore (0-100), insights[] with severity/signal/evidence/suggestion, and patterns (chronotype, peakHours, workload). 5 detectors: productivity, procrastination, task-structure, goal-alignment, workload.
AI agents call analyzeBehavior to retrieve information from Knowledge MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
analyzeBehavior performs algorithmic analysis on existing data to generate metrics and insights. It reads behavior patterns and produces analytical outputs without modifying the knowledge base, executing commands, or causing irreversible changes. This is a read-only analytical tool. Severity is low because misuse (e.g., analyzing a user's patterns without consent) causes informational leakage, not operational damage.
From the tool's definition Tool description states it 'Returns healthScore, insights[], and patterns' - purely analytical output with 'no LLM' processing. No mutations ('addKnowledge', 'addNote', 'addTask' are siblings that modify state).
Attacks that exploit this kind of access
Algorithmic behavior analysis (no LLM). Returns healthScore (0-100), insights[] with severity/signal/evidence/suggestion, and patterns (chronotype, peakHours, workload). 5 detectors: productivity, procrastination, task-structure, goal-alignment, workload. It is categorised as a Read tool in the Knowledge MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Knowledge MCP Server MCP server in PolicyLayer and add a rule for analyzeBehavior: 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 Knowledge MCP Server. Nothing to install.
analyzeBehavior 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 analyzeBehavior 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 analyzeBehavior. 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.
analyzeBehavior is provided by the Knowledge MCP Server MCP server (vuluu2k/knowledge_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 →