Bootstrap the session with glossary and dataset guidance.
AI agents call init_session to retrieve information from Aurora-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool loads and provides informational data to establish session context. It has no side effects, does not modify or delete data, does not execute external code, and does not involve financial transactions. It is a setup/initialization Read operation with minimal blast radius if misused—worst case being retrieving reference information unnecessarily.
From the tool's definition Tool name 'init_session' with description 'Bootstrap the session with glossary and dataset guidance' performs initialization/setup operations that retrieve reference data (glossary, dataset guidance).
Attacks that exploit this kind of access
Bootstrap the session with glossary and dataset guidance. It is categorised as a Read tool in the Aurora-MCP MCP Server, which means it retrieves data without modifying state.
Register the Aurora- MCP server in PolicyLayer and add a rule for init_session: 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 Aurora-MCP. Nothing to install.
init_session 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 init_session 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 init_session. 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.
init_session is provided by the Aurora- MCP server (ndaniel/aurora-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 →