recall

Search memories by relevance. Corrections surface first.

Server NeverOnce weberg619/neveronce
Category Read
Risk class Low
Parameters 00 required

What recall does on NeverOnce

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

Why recall needs a policy

Even though recall only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.

Questions about recall

What does the recall tool do? +

Search memories by relevance. Corrections surface first. It is categorised as a Read tool in the NeverOnce MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on recall? +

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

What risk level is recall? +

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

Can I rate-limit recall? +

Yes. Add a rate_limit block to the recall 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 recall completely? +

Set action: deny in the PolicyLayer policy for recall. 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 recall? +

recall is provided by the NeverOnce MCP server (weberg619/neveronce). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.