Low Risk

kage_graph_visual

Export the repo-local Kage knowledge graph as Mermaid flowchart text for visual inspection.

How to control kage_graph_visual ↓

What kage_graph_visual does on Kage

AI agents call kage_graph_visual to retrieve information from Kage without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

Why kage_graph_visual needs a policy

This tool reads and exports existing graph data as a text-based visualization (Mermaid flowchart). It performs no writes, deletions, or executions — purely retrieves and formats data for inspection. Severity is low since misuse would only expose internal knowledge graph structure.

From the tool's definition Export the repo-local Kage knowledge graph as Mermaid flowchart text for visual inspection.

Documented attack patterns abuse exactly the kind of access kage_graph_visual gives an agent:

How to control kage_graph_visual

PolicyLayer is an MCP gateway — it sits between your AI agents and Kage, and nothing reaches the server without passing your rules. This is the rule we recommend for kage_graph_visual:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "kage_graph_visual": {}
  }
}

kage_graph_visual is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Kage — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about kage_graph_visual

What does the kage_graph_visual tool do? +

Export the repo-local Kage knowledge graph as Mermaid flowchart text for visual inspection. It is categorised as a Read tool in the Kage MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on kage_graph_visual? +

Register the Kage MCP server in PolicyLayer and add a rule for kage_graph_visual: 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 Kage. Nothing to install.

What risk level is kage_graph_visual? +

kage_graph_visual is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit kage_graph_visual? +

Yes. Add a rate_limit block to the kage_graph_visual 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 kage_graph_visual completely? +

Set action: deny in the PolicyLayer policy for kage_graph_visual. 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 kage_graph_visual? +

kage_graph_visual is provided by the Kage MCP server (@kage-core/kage-graph-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Kage tool call.

Start from Kage, 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.

62 Kage tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.