List Hermes Agent (NousResearch) sessions visible on this machine. Scans $HERMES_HOME (default ~/.hermes) for state.db plus any profiles/<name>/state.db. Hermes conversations are GLOBAL — results are NOT filtered by the current project. Read-only. Returns JSON: { enabled, sessions: [{ sessionId, ...
AI agents call discover_hermes_sessions to retrieve information from Trace 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 queries and retrieves session metadata from Hermes Agent state databases. However, severity is elevated to 'high' because: (1) Hermes conversations are described as 'GLOBAL' and not filtered by project, meaning an agent could discover sessions from unrelated, potentially sensitive work; (2) session data may contain context about ongoing conversations, timestamps, and profile information…
From the tool's definition Tool description explicitly states: 'List Hermes Agent sessions', 'Scans $HERMES_HOME', 'Read-only', 'Returns JSON'. The tool retrieves and queries session data without modification.
Documented attack patterns abuse exactly the kind of access discover_hermes_sessions gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Trace, and nothing reaches the server without passing your rules. This is the rule we recommend for discover_hermes_sessions:
{
"version": "1",
"default": "deny",
"tools": {
"discover_hermes_sessions": {}
}
}discover_hermes_sessions 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.
List Hermes Agent (NousResearch) sessions visible on this machine. Scans $HERMES_HOME (default ~/.hermes) for state.db plus any profiles/<name>/state.db. Hermes conversations are GLOBAL — results are NOT filtered by the current project. Read-only. Returns JSON: { enabled, sessions: [{ sessionId, sourcePath, profile, lastActivity, sizeBytes }], total }. It is categorised as a Read tool in the Trace MCP Server, which means it retrieves data without modifying state.
Register the Trace MCP server in PolicyLayer and add a rule for discover_hermes_sessions: 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 Trace. Nothing to install.
discover_hermes_sessions 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 discover_hermes_sessions 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 discover_hermes_sessions. 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.
discover_hermes_sessions is provided by the Trace MCP server (nikolai-vysotskyi/trace-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 178 Trace tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
178 Trace tools catalogued and risk-classified — across an index of 42,500+ MCP servers.