AI agents use pause_session to create or update resources in TDD-MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your TDD-MCP environment.
Pausing a session modifies session state reversibly—it can be resumed (as evidenced by the sibling tool 'resume_session'). This is a state change operation without destructive intent, placing it in the Write category. The severity is low because pausing a TDD session has minimal blast radius: it simply suspends progress tracking without affecting code, data, or external systems. The action is easily reversible.
From the tool's definition Tool pauses (modifies the state of) the current active session, changing it from active to paused. The server description indicates 'session state management and phase transitions,' confirming that pause_session performs a state modification operation.
Attacks that exploit this kind of access
Pause the current active session. It is categorised as a Write tool in the TDD-MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the TDD- MCP server in PolicyLayer and add a rule for pause_session: 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 TDD-MCP. Nothing to install.
pause_session is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the pause_session 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 pause_session. 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.
pause_session is provided by the TDD- MCP server (tinmancoding/tdd-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 →