hyperbolic_entailment_graph · Claude Flow MCP: Risk & Policy

WHAT IT DOES

What hyperbolic_entailment_graph does on Claude Flow

AI agents invoke hyperbolic_entailment_graph to trigger actions in Claude Flow. 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.

WHY IT NEEDS A POLICY

Why hyperbolic_entailment_graph needs a policy

The tool both builds (constructs/modifies) and queries entailment graphs, spanning Write and Read. The 'pruning strategies' imply potential irreversible removal of graph edges/nodes, but this is within a computational graph structure rather than persistent user data. The dominant action is executing a graph construction and traversal algorithm with side effects on the graph structure, placing it in Execute.

From the tool's definition "Build and query entailment graphs using hyperbolic embeddings. Supports transitive closure and pruning strategies."

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

hyperbolic_entailment_graph Rate-limited

hyperbolic_entailment_graph 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "hyperbolic_entailment_graph": {
      "limits": [
        {
          "counter": "hyperbolic_entailment_graph_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Claude Flow, so you can run agents against it safely.

FAQ

Questions about hyperbolic_entailment_graph

What does the hyperbolic_entailment_graph tool do? +

Build and query entailment graphs using hyperbolic embeddings. Supports transitive closure and pruning strategies. It is categorised as a Execute tool in the Claude Flow MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on hyperbolic_entailment_graph? +

Register the Claude Flow MCP server in PolicyLayer and add a rule for hyperbolic_entailment_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 Claude Flow. Nothing to install.

What risk level is hyperbolic_entailment_graph? +

hyperbolic_entailment_graph is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit hyperbolic_entailment_graph? +

Yes. Add a rate_limit block to the hyperbolic_entailment_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.

How do I block hyperbolic_entailment_graph completely? +

Set action: deny in the PolicyLayer policy for hyperbolic_entailment_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.

What MCP server provides hyperbolic_entailment_graph? +

hyperbolic_entailment_graph is provided by the Claude Flow MCP server (claude-flow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.