Search for nodes in the knowledge graph based on one or more keywords. The search covers entity names, types, subdomains, and observation content. Multiple keywords are treated as OR conditions, where any keyword must match somewhere in the entity
AI agents call search_nodes to retrieve information from Knowledge Graph Memory Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
search_nodes retrieves and queries data from the knowledge graph without side effects. It performs a read-only lookup operation to find entities matching keywords. This is a classic Read category tool—no data is created, modified, deleted, or executed. The low severity reflects the minimal risk from an AI agent misusing a search function, as it can only retrieve existing data without altering system state.
From the tool's definition Tool description states it 'Search[es] for nodes in the knowledge graph' and 'covers entity names, types, subdomains, and observation content.' The function is explicitly a search/query operation with no modification, deletion, or execution capabilities.
Documented attack patterns abuse exactly the kind of access search_nodes gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Knowledge Graph Memory Server, and nothing reaches the server without passing your rules. This is the rule we recommend for search_nodes:
{
"version": "1",
"default": "deny",
"tools": {
"search_nodes": {}
}
}search_nodes 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 for nodes in the knowledge graph based on one or more keywords. The search covers entity names, types, subdomains, and observation content. Multiple keywords are treated as OR conditions, where any keyword must match somewhere in the entity. It is categorised as a Read tool in the Knowledge Graph Memory Server MCP Server, which means it retrieves data without modifying state.
Register the Knowledge Graph Memory Server MCP server in PolicyLayer and add a rule for search_nodes: 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 Knowledge Graph Memory Server. Nothing to install.
search_nodes 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 search_nodes 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 search_nodes. 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.
search_nodes is provided by the Knowledge Graph Memory Server MCP server (yodakeisuke/mcp-memory-domain-knowledge). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Knowledge Graph Memory Server, 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.
9 Knowledge Graph Memory Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.