Show or hide repos marked as type
AI agents use toggle_reference_repos to create or update resources in Agentic Bits Claude Plugin — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Agentic Bits Claude Plugin environment.
This tool modifies the display/visibility configuration of repositories marked as reference type. It's a reversible state change (toggling visibility on/off), making it a Write operation. The blast radius is low since it only affects UI visibility settings, not actual repository data.
From the tool's definition 'Show or hide repos marked as type' — toggles visibility state of reference repositories
Attacks that exploit this kind of access
Show or hide repos marked as type. It is categorised as a Write tool in the Agentic Bits Claude Plugin MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Agentic Bits Claude Plugin MCP server in PolicyLayer and add a rule for toggle_reference_repos: 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 Agentic Bits Claude Plugin. Nothing to install.
toggle_reference_repos 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 toggle_reference_repos 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 toggle_reference_repos. 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.
toggle_reference_repos is provided by the Agentic Bits Claude Plugin MCP server (onesmartguy/agentic-bits-claude-plugin). 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 →