Step 2: Get context around results. Params: anchor (observation ID) OR query (finds anchor automatically), depth_before, depth_after, project
AI agents call timeline to retrieve information from Claude Recall without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool exclusively retrieves and queries data from persistent memory storage to provide contextual information around a given observation. There are no side effects, no data modifications, and no irreversible actions. It functions as a contextual lookup mechanism, which is characteristic of Read operations.
From the tool's definition Tool is designed to 'Get context around results' by retrieving observations using an anchor ID or query-based lookup, with parameters controlling how much historical context is retrieved (depth_before, depth_after).
Documented attack patterns abuse exactly the kind of access timeline gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Claude Recall, and nothing reaches the server without passing your rules. This is the rule we recommend for timeline:
{
"version": "1",
"default": "deny",
"tools": {
"timeline": {}
}
}timeline 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.
Step 2: Get context around results. Params: anchor (observation ID) OR query (finds anchor automatically), depth_before, depth_after, project. It is categorised as a Read tool in the Claude Recall MCP Server, which means it retrieves data without modifying state.
Register the Claude Recall MCP server in PolicyLayer and add a rule for 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 Claude Recall. Nothing to install.
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 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 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.
timeline is provided by the Claude Recall MCP server (nhevers/moltbrain). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 3 Claude Recall tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
3 Claude Recall tools catalogued and risk-classified — across an index of 42,500+ MCP servers.