AI agents call read_graph to retrieve information from Elasticsearch Knowledge Graph for MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves/queries data from the knowledge graph without side effects. It performs a read-only operation on stored information. While reading an entire graph could return large volumes of data, the operation itself is non-destructive and reversible, placing it squarely in the Read category. Severity is low because reading data poses minimal risk compared to modification or deletion operations.
From the tool's definition Tool name 'read_graph' and description 'Read the entire knowledge graph' explicitly indicate a retrieval operation with no modification, deletion, or execution semantics.
Risk signalsBulk/mass operation — affects multiple targets
Documented attack patterns abuse exactly the kind of access read_graph gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Elasticsearch Knowledge Graph for MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for read_graph:
{
"version": "1",
"default": "deny",
"tools": {
"read_graph": {}
}
}read_graph 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.
Read the entire knowledge graph. It is categorised as a Read tool in the Elasticsearch Knowledge Graph for MCP MCP Server, which means it retrieves data without modifying state.
Register the Elasticsearch Knowledge Graph for MCP server in PolicyLayer and add a rule for read_graph: 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 Elasticsearch Knowledge Graph for MCP. Nothing to install.
read_graph 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 read_graph 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 read_graph. 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.
read_graph is provided by the Elasticsearch Knowledge Graph for MCP server (j3k0/mcp-brain-tools). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Elasticsearch Knowledge Graph for MCP, 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.
23 Elasticsearch Knowledge Graph for MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.