AI agents call quick_help 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 and displays help information based on the current session state. It only reads/queries state to surface contextual guidance — no data is created, modified, deleted, or executed. Blast radius is minimal as misuse would only result in displaying irrelevant help text.
From the tool's definition 'Provide context-aware shortcuts and help based on current session state'
Attacks that exploit this kind of access
Provide context-aware shortcuts and help based on current session state. 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 quick_help: 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.
quick_help 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 quick_help 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 quick_help. 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.
quick_help 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 →