training_ingest
Ingest raw training material from files, memory, code, or text. Stores in training_sources table for later pair generation. Sources: memory files, .js/.ts code, .md docs, raw text, API patterns. Example: training_ingest({ source_type:
This record as markdown: /tools/io-github-0nork-0nmcp/training-ingest.md
What training_ingest does on 0nmcp
AI agents use training_ingest to create or update resources in 0nmcp, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your 0nmcp environment.
Why training_ingest is rated Medium
This tool writes data to a database table (training_sources). It ingests content from various sources and persists it for future use. This is a reversible write operation — data is stored but not irreversibly destroyed. Severity is medium because an AI agent could inadvertently store sensitive or malicious content into a training pipeline.
From the tool's definition Ingest raw training material... Stores in training_sources table for later pair generation.
Attacks that exploit this kind of access
The rule that runs training_ingest safely
PolicyLayer is an MCP gateway: it sits between your AI agents and 0nmcp, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For training_ingest, this is the rule to start with:
training_ingest stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect 0nmcp, apply this rule, and every training_ingest call is checked against it from then on.
Questions about training_ingest
Ingest raw training material from files, memory, code, or text. Stores in training_sources table for later pair generation. Sources: memory files, .js/.ts code, .md docs, raw text, API patterns. Example: training_ingest({ source_type:. It is categorised as a Write tool in the 0nmcp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the 0n MCP server in PolicyLayer and add a rule for training_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 0nmcp. Nothing to install.
training_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 training_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 training_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.
training_ingest is provided by the 0n MCP server (0nmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on 0n, and thousands of servers like it.
This server
Across the catalogue