Searches TP cards (UserStories or Bugs) by keyword or phrase or partial keyphrase in Card Description e.g.
AI agents call search_tp_cards to retrieve information from Targetprocess without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Even though search_tp_cards only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
Searches TP cards (UserStories or Bugs) by keyword or phrase or partial keyphrase in Card Description e.g. It is categorised as a Read tool in the Targetprocess MCP Server, which means it retrieves data without modifying state.
Register the Targetprocess MCP server in PolicyLayer and add a rule for search_tp_cards: 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 Targetprocess. Nothing to install.
search_tp_cards 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 search_tp_cards 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 search_tp_cards. 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.
search_tp_cards is provided by the Targetprocess MCP server (targetprocess-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.