Validate a use-case diagramModel JSON BEFORE generating the HTML file. Catches the §4/§4.4/CR violations the prompt cannot fully enforce: include target with actor association (CR #4), single-incoming include (CR #4), send-only UC names (CR #10), physical-verb names (CR #8), missing primary actor...
Part of the Sad MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call uml_usecase_validate_model to retrieve information from Sad without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though uml_usecase_validate_model only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
tools:
uml_usecase_validate_model:
rules:
- action: allowSee the full Sad policy for all 15 tools.
Agents calling read-class tools like uml_usecase_validate_model have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.
Validate a use-case diagramModel JSON BEFORE generating the HTML file. Catches the §4/§4.4/CR violations the prompt cannot fully enforce: include target with actor association (CR #4), single-incoming include (CR #4), send-only UC names (CR #10), physical-verb names (CR #8), missing primary actor (§4.4), broken references in scenario flow steps, orphaned UCs, and unsafe wireframe HTML. Returns either 'Model valid' (optionally with warnings) or a list of specific errors to fix. Call iteratively — fix errors, call again — until valid. This check runs locally; no API cost.. It is categorised as a Read tool in the Sad MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for uml_usecase_validate_model. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Sad MCP server.
uml_usecase_validate_model 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 uml_usecase_validate_model rule in your Intercept 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 Intercept policy for uml_usecase_validate_model. 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.
uml_usecase_validate_model is provided by the Sad MCP server (sad-mcp). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.