Search memories with temporal scoring + observation filtering.
AI agents call memory_search to retrieve information from Jarvis Orb without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves data from a memory system using search parameters and filters. The verbs 'search' and 'filtering' are characteristic of Read operations. There is no evidence of data creation, modification, deletion, code execution, or financial impact. The temporal scoring and observation filtering are search refinement mechanisms, not write or destructive actions.
From the tool's definition Tool name 'memory_search' and description 'Search memories with temporal scoring + observation filtering' indicate a retrieval operation with no modification or side effects.
Documented attack patterns abuse exactly the kind of access memory_search gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Jarvis Orb, and nothing reaches the server without passing your rules. This is the rule we recommend for memory_search:
{
"version": "1",
"default": "deny",
"tools": {
"memory_search": {}
}
}memory_search 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.
Search memories with temporal scoring + observation filtering. It is categorised as a Read tool in the Jarvis Orb MCP Server, which means it retrieves data without modifying state.
Register the Jarvis Orb MCP server in PolicyLayer and add a rule for memory_search: 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 Jarvis Orb. Nothing to install.
memory_search 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 memory_search 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 memory_search. 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.
memory_search is provided by the Jarvis Orb MCP server (thestack-ai/jarvis-orb). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Jarvis Orb, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
7 Jarvis Orb tools catalogued and risk-classified — across an index of 43,000+ MCP servers.