Get recent tool call history from the audit log. Useful for debugging.
AI agents call get_recent_tool_calls to retrieve information from OODA Computer Control without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a Read operation—it retrieves data from the audit log without side effects. However, severity is elevated to medium because audit logs may contain sensitive information about system commands, file paths, credentials in arguments, or other privileged operations executed on the system. An AI agent with this tool could reconstruct attack sequences or discover sensitive data inadvertently logged.
From the tool's definition Tool name and description indicate retrieval of historical data: 'Get recent tool call history from the audit log.' No modification, deletion, or execution capabilities described. The function purely queries and returns existing audit log entries.
Documented attack patterns abuse exactly the kind of access get_recent_tool_calls gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and OODA Computer Control, and nothing reaches the server without passing your rules. This is the rule we recommend for get_recent_tool_calls:
{
"version": "1",
"default": "deny",
"tools": {
"get_recent_tool_calls": {}
}
}get_recent_tool_calls is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get recent tool call history from the audit log. Useful for debugging. It is categorised as a Read tool in the OODA Computer Control MCP Server, which means it retrieves data without modifying state.
Register the OODA Computer Control MCP server in PolicyLayer and add a rule for get_recent_tool_calls: 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 OODA Computer Control. Nothing to install.
get_recent_tool_calls 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_recent_tool_calls 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_recent_tool_calls. 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_recent_tool_calls is provided by the OODA Computer Control MCP server (mnehmos/mnehmos.ooda.mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from OODA Computer Control, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
99 OODA Computer Control tools catalogued and risk-classified — across an index of 43,000+ MCP servers.