Performs deep web research on a query and stores the findings as atomic notes. Uses Google Search API (if configured) or DuckDuckGo for web search, Jina Reader (local Docker or cloud) for web content extraction, and Unstructured for PDF extraction. Automatically detects PDF URLs and uses appropri...
AI agents invoke research_and_store to trigger actions in A-MEM: Agentic Memory System. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool both executes external operations (web searches via Google/DuckDuckGo, web content extraction via Jina Reader, PDF extraction via Unstructured) and writes data to the memory system. Since it triggers external network requests and also stores results, it spans Execute and Write categories. Execute is more severe than Write, so Execute is selected.
From the tool's definition Performs deep web research on a query and stores the findings as atomic notes. Uses Google Search API, DuckDuckGo, Jina Reader for web content extraction, and Unstructured for PDF extraction.
Documented attack patterns abuse exactly the kind of access research_and_store gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and A-MEM: Agentic Memory System, and nothing reaches the server without passing your rules. This is the rule we recommend for research_and_store:
{
"version": "1",
"default": "deny",
"tools": {
"research_and_store": {
"limits": [
{
"counter": "research_and_store_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}research_and_store stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Performs deep web research on a query and stores the findings as atomic notes. Uses Google Search API (if configured) or DuckDuckGo for web search, Jina Reader (local Docker or cloud) for web content extraction, and Unstructured for PDF extraction. Automatically detects PDF URLs and uses appropriate extraction method. Results are stored as atomic notes in the memory system with automatic linking and evolution. It is categorised as a Execute tool in the A-MEM: Agentic Memory System MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the A-MEM: Agentic Memory System MCP server in PolicyLayer and add a rule for research_and_store: 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 A-MEM: Agentic Memory System. Nothing to install.
research_and_store is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the research_and_store 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 research_and_store. 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.
research_and_store is provided by the A-MEM: Agentic Memory System MCP server (tobs-code/a-mem-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from A-MEM: Agentic Memory System, 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.
15 A-MEM: Agentic Memory System tools catalogued and risk-classified — across an index of 43,000+ MCP servers.