AI agents use end_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.
This tool performs a write operation by modifying session state (marking a session as ended/inactive). While it does not create new data or delete historical records, it irreversibly changes the status of the current session. It is not a Read operation because it has side effects beyond querying. It is not Destructive because the session data and history remain intact (the history tool is available as a sibling).
From the tool's definition The tool description states it will "End the current active session and return summary." Ending a session modifies the state of the session management system by terminating an active session, which is a state change operation.
Attacks that exploit this kind of access
End the current active session and return summary. 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 end_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.
end_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 end_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 end_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.
end_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 →