ons_query
AI agents call ons_query 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.
Query operations on knowledge graphs are read operations that retrieve data via semantic search or lookup without side effects. While the description is uninformative, the tool name and context of sibling write/delete/modify operations establish that 'ons_query' is the read counterpart. Confidence is slightly reduced due to missing explicit description, but naming conventions are reliable indicators.
From the tool's definition Tool name 'ons_query' with sibling tools including ons_ingest, ons_upsert, ons_delete, and ons_rewire indicates a knowledge graph system. Query tools in such systems retrieve or search data without modification.
Attacks that exploit this kind of access
ons_query. 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_query: 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_query 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_query 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_query. 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_query 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 →