remember_search_space_by

Search published memories in shared spaces/groups using specialized sort/discovery modes. Modes: - byTime: Chronological sort (newest/oldest first) - byRating: Sort by Bayesian rating average (social ratings from other users) - byDiscovery: Interleaved rated + unrated content for exploration (4:1...

Server Remember @prmichaelsen/remember-mcp
Category Read
Risk class Low
Parameters 00 required

What remember_search_space_by does on Remember

AI agents call remember_search_space_by to retrieve information from Remember without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why remember_search_space_by needs a policy

This tool retrieves and queries data from a shared memory system with various sorting and filtering options. The description explicitly states it searches published memories and provides different discovery modes. No write, execute, destructive, or financial operations are performed—only data retrieval and presentation.

From the tool's definition Tool performs search and discovery operations: 'Search published memories in shared spaces/groups using specialized sort/discovery modes' with modes like 'byTime' (chronological sort), 'byRating' (sort by ratings), 'byDiscovery' (exploration), 'byProperty'…

Questions about remember_search_space_by

What does the remember_search_space_by tool do? +

Search published memories in shared spaces/groups using specialized sort/discovery modes. Modes: - byTime: Chronological sort (newest/oldest first) - byRating: Sort by Bayesian rating average (social ratings from other users) - byDiscovery: Interleaved rated + unrated content for exploration (4:1 ratio). Good for finding hidden gems. - byProperty: Sort by any memory property (e.g., feel_trauma, total_significance, weight). Requires sort_field. - byBroad: Massive results with truncated content (content_head/mid/tail ~100 chars each) for scan-and-drill-in workflow - byRandom: Random sampling for serendipitous discovery At least one of. It is categorised as a Read tool in the Remember MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on remember_search_space_by? +

Register the Remember MCP server in PolicyLayer and add a rule for remember_search_space_by: 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 Remember. Nothing to install.

What risk level is remember_search_space_by? +

remember_search_space_by is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit remember_search_space_by? +

Yes. Add a rate_limit block to the remember_search_space_by 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.

How do I block remember_search_space_by completely? +

Set action: deny in the PolicyLayer policy for remember_search_space_by. 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.

What MCP server provides remember_search_space_by? +

remember_search_space_by is provided by the Remember MCP server (@prmichaelsen/remember-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// LOOK UP ANOTHER 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 →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.