Open and retrieve specific entities by their names
AI agents call open_nodes to retrieve information from Knowledge Graph MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves specific entities from the knowledge graph by name, with no side effects. This is a pure read/fetch operation.
From the tool's definition "Open and retrieve specific entities by their names"
Attacks that exploit this kind of access
Open and retrieve specific entities by their names. It is categorised as a Read tool in the Knowledge Graph MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Knowledge Graph MCP Server MCP server in PolicyLayer and add a rule for open_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 MCP Server. Nothing to install.
open_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 open_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 open_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.
open_nodes is provided by the Knowledge Graph MCP Server MCP server (yuchoe/knowledge-graph-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →