List recent captured requests that hit a mock endpoint. Use this to verify your integration is actually calling the mock URL — shows method, path, status, and time for each capture. Returns up to 50 by default.
AI agents call list_mock_captures to retrieve information from RequestBin MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
list_mock_captures retrieves and displays historical data about HTTP requests that have been captured by a mock endpoint. It performs no mutations, deletions, or external operations. The tool is read-only inspection of previously captured webhook data, making it a Read category risk.
From the tool's definition Tool description explicitly states 'List recent captured requests' and 'shows method, path, status, and time for each capture' — purely informational retrieval with no modification or side effects.
Attacks that exploit this kind of access
List recent captured requests that hit a mock endpoint. Use this to verify your integration is actually calling the mock URL — shows method, path, status, and time for each capture. Returns up to 50 by default. It is categorised as a Read tool in the RequestBin MCP Server MCP Server, which means it retrieves data without modifying state.
Register the RequestBin MCP Server MCP server in PolicyLayer and add a rule for list_mock_captures: 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 RequestBin MCP Server. Nothing to install.
list_mock_captures 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 list_mock_captures 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 list_mock_captures. 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.
list_mock_captures is provided by the RequestBin MCP Server MCP server (requestbin/mcp-server). 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 →