Run AVA via npx with JSON (or TAP) output and return aggregated results. For long-running watchers, use tdd_start_watch/tdd_get_watch_changes instead.
AI agents invoke tdd_run_tests to trigger actions in Promethean OS MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes code (test suites) via npx, making it an Execute category tool. The severity is medium rather than high because test execution is typically constrained to test files in a controlled context, limiting the blast radius compared to unrestricted shell execution. However, if tests have side effects or malicious code, an AI agent could trigger unintended operations.
From the tool's definition The tool description states it "Run[s] AVA via npx with JSON (or TAP) output". The verb "run" combined with "via npx" (Node Package eXecute) indicates execution of external code/processes. AVA is a JavaScript test runner that executes arbitrary test code.
Attacks that exploit this kind of access
Run AVA via npx with JSON (or TAP) output and return aggregated results. For long-running watchers, use tdd_start_watch/tdd_get_watch_changes instead. It is categorised as a Execute tool in the Promethean OS MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Promethean OS MCP server in PolicyLayer and add a rule for tdd_run_tests: 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 Promethean OS MCP. Nothing to install.
tdd_run_tests is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the tdd_run_tests 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 tdd_run_tests. 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.
tdd_run_tests is provided by the Promethean OS MCP server (octave-commons/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 →