Creates work distribution groups from violations report. Reads a violations JSON file (e.g., packages-poker-violations.json) from ${DEFAULT_OUTPUT_BASE}/${OUTPUT_SUBDIRS.VIOLATIONS_REPORT}/ and creates balanced work groups using bin-packing algorithm. Accepts both file-grouped and component-group...
AI agents call group-violations to retrieve information from Angular Toolkit MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs data retrieval and transformation for analysis purposes. It reads a violations report file and processes it into organized groups using a bin-packing algorithm. There are no side effects on the codebase, no destructive operations, no code execution, and no financial implications.
From the tool's definition The tool 'Reads a violations JSON file' and 'creates work distribution groups' - it retrieves and processes existing violation data to organize it into groups. No data is modified, deleted, or external operations triggered.
Attacks that exploit this kind of access
Creates work distribution groups from violations report. Reads a violations JSON file (e.g., packages-poker-violations.json) from ${DEFAULT_OUTPUT_BASE}/${OUTPUT_SUBDIRS.VIOLATIONS_REPORT}/ and creates balanced work groups using bin-packing algorithm. Accepts both file-grouped and component-grouped violation reports. Groups are balanced by violation count, maintain path exclusivity (each file in one group), and preserve directory boundaries for parallel development. It is categorised as a Read tool in the Angular Toolkit MCP MCP Server, which means it retrieves data without modifying state.
Register the Angular Toolkit MCP server in PolicyLayer and add a rule for group-violations: 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 Angular Toolkit MCP. Nothing to install.
group-violations 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 group-violations 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 group-violations. 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.
group-violations is provided by the Angular Toolkit MCP server (push-based/angular-toolkit-mcp). 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 →