browse_graph
AI agents call browse_graph to retrieve information from Timepoint MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to query or traverse the causal graph of historical events based on naming patterns and server context. While the description is empty (lowering confidence slightly), the sibling tools and overall server purpose (providing 'structured access' to a knowledge platform) strongly suggest this is a read operation for exploring graph connections and relationships.
From the tool's definition Tool name 'browse_graph' and sibling tools like 'get_connections', 'graph_stats', 'search_moments', 'get_moment' and 'random_moment' indicate a read-focused API.
Attacks that exploit this kind of access
browse_graph. It is categorised as a Read tool in the Timepoint MCP MCP Server, which means it retrieves data without modifying state.
Register the Timepoint MCP server in PolicyLayer and add a rule for browse_graph: 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 Timepoint MCP. Nothing to install.
browse_graph 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 browse_graph 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 browse_graph. 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.
browse_graph is provided by the Timepoint MCP server (timepointai/timepoint-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
browse_graph is one line of Timepoint's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →