Dump the full graph as {nodes: [...], edges: [...]}.
AI agents call graph_snapshot to retrieve information from State Trace without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and returns the current state of an in-memory graph structure. 'Dump' in this context means to export or serialize data for inspection, a read-only operation. No write, execute, destructive, or financial operations are performed.
From the tool's definition Tool name 'graph_snapshot' and description 'Dump the full graph' indicate a retrieval/query operation with no modification or deletion of data. The output format {nodes, edges} confirms it returns a data snapshot rather than executing side effects.
Attacks that exploit this kind of access
Dump the full graph as {nodes: [...], edges: [...]}. It is categorised as a Read tool in the State Trace MCP Server, which means it retrieves data without modifying state.
Register the State Trace MCP server in PolicyLayer and add a rule for graph_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 State Trace. Nothing to install.
graph_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 graph_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 graph_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.
graph_snapshot is provided by the State Trace MCP server (agent-pattern-labs/state-trace). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →