AI agents call graph_analysis to retrieve information from Tages without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and analyzes existing graph data to provide insights. It has no side effects, does not modify the codebase or memory store, does not execute code, and does not delete or financially impact anything. It is a read-only analytical operation, similar to generating reports or metrics from stored data.
From the tool's definition The tool performs 'analyze' operations on a 'memory dependency graph' to identify 'orphans, critical paths, impact scores' — pure analysis with no modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
Analyze the memory dependency graph — orphans, critical paths, impact scores. It is categorised as a Read tool in the Tages MCP Server, which means it retrieves data without modifying state.
Register the Tages MCP server in PolicyLayer and add a rule for graph_analysis: 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 Tages. Nothing to install.
graph_analysis 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 graph_analysis 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 graph_analysis. 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.
graph_analysis is provided by the Tages MCP server (ryantlee25-droid/tages). 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 →