AI agents use save_session to create or update resources in Binary MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Binary MCP Server environment.
The tool creates or modifies session state files reversibly—a Write operation. It cannot delete or execute arbitrary code directly, but could potentially overwrite previous analysis sessions. Severity is medium because misuse would affect only stored analysis metadata, not underlying system or data. Confidence is 0.75 due to empty description; inferred intent from tool name and server context.
From the tool's definition Tool name 'save_session' indicates persistence of debugging/analysis state. Server description mentions 'Ghidra, x64dbg, WinDbg' which are debuggers where session state includes breakpoints, watches, and analysis metadata. Saving modifies persistent storage.
Documented attack patterns abuse exactly the kind of access save_session gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Binary MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for save_session:
{
"version": "1",
"default": "deny",
"tools": {
"save_session": {
"limits": [
{
"counter": "save_session_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}save_session stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
save_session. It is categorised as a Write tool in the Binary MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Binary MCP Server MCP server in PolicyLayer and add a rule for save_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 Binary MCP Server. Nothing to install.
save_session is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the save_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 save_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.
save_session is provided by the Binary MCP Server MCP server (sarks0/binary-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Binary MCP Server, 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.
59 Binary MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.