Build a knowledge graph from extracted entities and relationships. Returns graph statistics including node count, edge count, density, and connected components. The graph can be filtered by entity types, minimum occurrence counts, and relationship strength thresholds.
AI agents call build_knowledge_graph to retrieve information from TDZ C64 Knowledge without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool builds/computes a knowledge graph representation from already-extracted entities and relationships, and returns statistics about it. This is fundamentally a read/query/analysis operation over existing data — it does not create, modify, delete, or execute external operations. The word 'build' could imply writing, but the description focuses on returning computed statistics rather than persisting new data.
From the tool's definition 'Build a knowledge graph from extracted entities and relationships. Returns graph statistics including node count, edge count, density, and connected components.'
Attacks that exploit this kind of access
Build a knowledge graph from extracted entities and relationships. Returns graph statistics including node count, edge count, density, and connected components. The graph can be filtered by entity types, minimum occurrence counts, and relationship strength thresholds. It is categorised as a Read tool in the TDZ C64 Knowledge MCP Server, which means it retrieves data without modifying state.
Register the TDZ C64 Knowledge MCP server in PolicyLayer and add a rule for build_knowledge_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 TDZ C64 Knowledge. Nothing to install.
build_knowledge_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 build_knowledge_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 build_knowledge_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.
build_knowledge_graph is provided by the TDZ C64 Knowledge MCP server (michaeltroelsen/tdz-c64-knowledge). 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 →