Search chronology by date range, parties, keywords, or tags
AI agents call search_timeline to retrieve information from Case Chronology without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and filters existing chronological data based on search criteria without modifying, deleting, or executing operations. It is a pure information-retrieval function typical of Read category tools. The low severity reflects minimal risk even if misused by an AI agent—it cannot alter case data or trigger external operations.
From the tool's definition Tool name 'search_timeline' and description 'Search chronology by date range, parties, keywords, or tags' indicate a read-only query operation with no side effects.
Attacks that exploit this kind of access
Search chronology by date range, parties, keywords, or tags. It is categorised as a Read tool in the Case Chronology MCP Server, which means it retrieves data without modifying state.
Register the Case Chronology MCP server in PolicyLayer and add a rule for search_timeline: 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 Case Chronology. Nothing to install.
search_timeline 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 search_timeline 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 search_timeline. 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.
search_timeline is provided by the Case Chronology MCP server (medelman17/case-chronology-mcp). 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 →