Retrieve all project branches (boltz) for the workspace. Boltz are like sprints or project phases that group related tasks. Use this first to get bolt_id values for filtering tasks by project area. Returns: id, name, description, status for each bolt.
AI agents call get_boltz to retrieve information from Nubis without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns project branch (boltz) metadata for the workspace without creating, modifying, deleting, or executing any operations. It serves as a lookup utility to obtain bolt_id values for use in filtering other operations. No side effects or data mutations occur.
From the tool's definition Tool description explicitly states 'Retrieve all project branches' and 'Returns: id, name, description, status for each bolt.' The verb 'Retrieve' and return of metadata without modification indicate read-only query functionality.
Attacks that exploit this kind of access
Retrieve all project branches (boltz) for the workspace. Boltz are like sprints or project phases that group related tasks. Use this first to get bolt_id values for filtering tasks by project area. Returns: id, name, description, status for each bolt. It is categorised as a Read tool in the Nubis MCP Server, which means it retrieves data without modifying state.
Register the Nubis MCP server in PolicyLayer and add a rule for get_boltz: 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 Nubis. Nothing to install.
get_boltz 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 get_boltz 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 get_boltz. 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.
get_boltz is provided by the Nubis MCP server (@lil2good/nubis-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 →