ATOMIC ACTION 3 of 3 (harvest what this agent just created). Call at the END of every task that produced reusable artifacts. Inspects changed or explicit local files and produces private-by-default reusable asset package drafts with metadata, usage examples, risk notes, compatibility, and quality...
AI agents use tokrepo_harvest to create or update resources in TokRepo — AI Asset Registry — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your TokRepo — AI Asset Registry environment.
This tool creates and packages new assets (writes draft packages with metadata, examples, and notes) but explicitly states 'Never publishes automatically', meaning the creation is reversible and requires explicit user action for distribution. The action is constructive (packaging) rather than destructive, and does not execute arbitrary code or trigger external operations—it organizes local artifacts into drafts.
From the tool's definition Tool 'produces private-by-default reusable asset package drafts' and 'inspects changed or explicit local files', creating new package metadata and documentation artifacts.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
ATOMIC ACTION 3 of 3 (harvest what this agent just created). Call at the END of every task that produced reusable artifacts. Inspects changed or explicit local files and produces private-by-default reusable asset package drafts with metadata, usage examples, risk notes, compatibility, and quality gates. Never publishes automatically —. It is categorised as a Write tool in the TokRepo — AI Asset Registry MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the TokRepo — AI Asset Registry MCP server in PolicyLayer and add a rule for tokrepo_harvest: 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 TokRepo — AI Asset Registry. Nothing to install.
tokrepo_harvest 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 tokrepo_harvest 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 tokrepo_harvest. 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.
tokrepo_harvest is provided by the TokRepo — AI Asset Registry MCP server (tokrepo-mcp-server). 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 →