AI agents invoke tm_pause_run to trigger actions in Tm. 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 a control action on an in-flight TrafficMorph run. Although it is not destructive (the run can be resumed) and does not delete or create data, it halts an active external operation. This is characteristic of Execute — triggering external operations whose effects depend on context (which run, what state it is in).
From the tool's definition 'Pause the in-flight run for a profile' — pauses an active load-testing or CI operation, which is an external action that affects a running process. The tool triggers an operation on an active system resource whose state changes based on invocation.
Attacks that exploit this kind of access
Pause the in-flight run for a profile. Idempotent — when no. It is categorised as a Execute tool in the Tm MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Tm MCP server in PolicyLayer and add a rule for tm_pause_run: 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 Tm. Nothing to install.
tm_pause_run 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 tm_pause_run 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 tm_pause_run. 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.
tm_pause_run is provided by the Tm MCP server (trafficmorph-gif/tm-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 →