Continue an agent session using stored conversation session ID with additional instructions
AI agents invoke continue_agent_session to trigger actions in ZMCPTools. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool resumes an autonomous agent session and injects additional instructions into it. The effects are highly dependent on what the agent session does — it could trigger code execution, browser automation, file modifications, or other high-impact operations. Since it drives autonomous agent behavior, it falls under Execute with high severity due to the broad blast radius of agent actions.
From the tool's definition Continue an agent session using stored conversation session ID with additional instructions
Documented attack patterns abuse exactly the kind of access continue_agent_session gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and ZMCPTools, and nothing reaches the server without passing your rules. This is the rule we recommend for continue_agent_session:
{
"version": "1",
"default": "deny",
"tools": {
"continue_agent_session": {
"limits": [
{
"counter": "continue_agent_session_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}continue_agent_session stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Continue an agent session using stored conversation session ID with additional instructions. It is categorised as a Execute tool in the ZMCPTools MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the ZMCPTools MCP server in PolicyLayer and add a rule for continue_agent_session: 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 ZMCPTools. Nothing to install.
continue_agent_session is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the continue_agent_session 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 continue_agent_session. 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.
continue_agent_session is provided by the ZMCPTools MCP server (zachhandley/zmcptools). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 70 ZMCPTools tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
70 ZMCPTools tools catalogued and risk-classified — across an index of 42,500+ MCP servers.