ons_session
AI agents call ons_session to retrieve information from Open Neural Substrate without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Without a description, confidence is reduced. However, the naming convention and context suggest this tool likely retrieves session information (Read category) rather than modifying or deleting data. If it were destructive or execute-level, it would likely have a more explicit name like ons_terminate_session. Classified as Read with low confidence due to insufficient documentation.
From the tool's definition Tool name 'ons_session' with empty description provides minimal information. In the context of a knowledge graph management system with other tools like ons_query (read), ons_ingest (write), ons_upsert (write), and ons_delete (destructive), 'session'…
Attacks that exploit this kind of access
ons_session. It is categorised as a Read tool in the Open Neural Substrate MCP Server, which means it retrieves data without modifying state.
Register the Open Neural Substrate MCP server in PolicyLayer and add a rule for ons_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 Open Neural Substrate. Nothing to install.
ons_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 ons_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 ons_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.
ons_session is provided by the Open Neural Substrate MCP server (pedroknigge/open-neural-substrate). 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 →