Compact session snapshot (~200 tokens) for context recovery after compaction. Returns focus files (by read count), edited files, key searches, and dead ends. Also used by the PreCompact hook to preserve session orientation automatically. Read-only. For full journal use get_session_journal; for cr...
AI agents call get_session_snapshot 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.
get_session_snapshot retrieves and queries existing session state data without side effects. It returns a compact snapshot of prior session context for navigation and memory recovery purposes. This is a straightforward read operation that poses minimal risk—misuse would only leak information about prior code navigation patterns, not enable destructive or financial actions.
From the tool's definition Tool description explicitly states 'Read-only' and 'Returns JSON' with session metadata (focusFiles, editedFiles, keySearches, deadEnds). No modification, deletion, or execution of external operations mentioned.
Documented attack patterns abuse exactly the kind of access get_session_snapshot 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 get_session_snapshot:
{
"version": "1",
"default": "deny",
"tools": {
"get_session_snapshot": {}
}
}get_session_snapshot 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.
Compact session snapshot (~200 tokens) for context recovery after compaction. Returns focus files (by read count), edited files, key searches, and dead ends. Also used by the PreCompact hook to preserve session orientation automatically. Read-only. For full journal use get_session_journal; for cross-session context use get_session_resume. Returns JSON: { focusFiles, editedFiles, keySearches, deadEnds }. 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 get_session_snapshot: 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.
get_session_snapshot 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_session_snapshot 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_session_snapshot. 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_session_snapshot 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.