ons_ingest
AI agents use ons_ingest to create or update resources in Open Neural Substrate — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Open Neural Substrate environment.
'Ingest' typically means importing or writing new data into a system. In the context of a knowledge graph server, this likely creates or adds new neuron entries. The empty description lowers confidence significantly. Severity is medium because ingesting data into a persistent knowledge graph could have meaningful side effects, but it appears reversible (sibling tool ons_delete exists).
From the tool's definition Tool name 'ons_ingest' on a server described as a knowledge graph manager with 'memory consolidation' capabilities; no description provided.
Attacks that exploit this kind of access
ons_ingest. It is categorised as a Write tool in the Open Neural Substrate MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Open Neural Substrate MCP server in PolicyLayer and add a rule for ons_ingest: 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_ingest is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the ons_ingest 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_ingest. 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_ingest 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 →