Generate a static surface contract for a component
AI agents call build_component_contract 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.
The tool generates/reads static analysis data about a component's surface contract (inputs, outputs, public API). 'Generate' here means computing/deriving information, not creating or modifying any files or data. It is purely analytical, similar to other read-only analysis tools on this server like 'build-component-usage-graph' and 'diff_component_contract'. No side effects are indicated.
From the tool's definition Generate a static surface contract for a component
Attacks that exploit this kind of access
Generate a static surface contract for a component. 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 build_component_contract: 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.
build_component_contract 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 build_component_contract 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 build_component_contract. 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.
build_component_contract 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 →