Get statistics about your current context window health. Returns: - Number of turns (user and assistant messages) - Estimated token count - Number of compaction/summary events - Context age Use this to decide when you might want to checkpoint or reset.
AI agents call get_context_stats to retrieve information from Context Travel MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays metadata about the current context state without modifying, executing, deleting, or committing any resources. It is diagnostic in nature, analogous to monitoring or status commands. The low severity reflects that misuse cannot cause harm—it only exposes read-only information to help the agent decide when to take other actions.
From the tool's definition Tool description states it 'Get statistics about your current context window health' and 'Returns: Number of turns, Estimated token count, Number of compaction/summary events, Context age.' These are purely informational queries with no side effects.
Attacks that exploit this kind of access
Get statistics about your current context window health. Returns: - Number of turns (user and assistant messages) - Estimated token count - Number of compaction/summary events - Context age Use this to decide when you might want to checkpoint or reset. It is categorised as a Read tool in the Context Travel MCP MCP Server, which means it retrieves data without modifying state.
Register the Context Travel MCP server in PolicyLayer and add a rule for get_context_stats: 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 Context Travel MCP. Nothing to install.
get_context_stats 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_context_stats 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_context_stats. 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_context_stats is provided by the Context Travel MCP server (simen/mcp-memento). 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 →