AI agents call get_current_state to retrieve information from TDD-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries the current state of a TDD session without modifying, executing external operations, or deleting data. It is a pure read operation that provides visibility into session state, making it Read category with low severity due to minimal potential for misuse—an AI agent querying session state poses negligible risk.
From the tool's definition Tool name 'get_current_state' and description 'Get current state of the active session' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
Get current state of the active session. It is categorised as a Read tool in the TDD-MCP MCP Server, which means it retrieves data without modifying state.
Register the TDD- MCP server in PolicyLayer and add a rule for get_current_state: 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.
get_current_state 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 get_current_state 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 get_current_state. 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.
get_current_state 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 →